# OpenFlux 3 — product guide for AI readers Canonical website: https://openflux3.com Create 5–20s 4K AI videos with native audio using FLUX 3 Max and FLUX 3 on OpenFlux 3, plus FLUX 3 Image, GPT Image 2.6 GIF/SVG, vendor LLM rendering, and Kie Seedance 2.5 face swap. OpenFlux 3 combines a FLUX 3 video and image studio (defaulting to FLUX 3 Max on the homepage), GPT Image 2.6 (with GIF and SVG support), multi-vendor LLM browser-rendered illustrations and motion graphics, Kie Seedance 2.5 trending face-swap templates, browser image utilities, and text rewriting. It is an independent website, not an official site of Black Forest Labs, fal, Kie, or any model provider. Model names identify available integrations, not affiliation or a guarantee of output quality. ## Find the right workspace - [Trending templates](https://openflux3.com/trending): fixed source-video workflows with Kie Seedance 2.5; choose the available format and roles. 23 themes / 32 creatable formats; preview-only themes cannot be submitted. Provider configuration is checked before checkout or generation. - [Prompt Seen](https://openflux3.com/prompt-seen): describe an uploaded image with fal OpenRouter Vision / Gemini 2.5 Flash, then edit, copy or download the prompt. - [Video studio](https://openflux3.com/ai-video-generator): select a model, choose its supported mode and inspect the settings and credit quote before creating. - [Image studio](https://openflux3.com/ai-image-generator): start with a prompt or an image supported by the selected model; layer decomposition is a separate mode. - [Motion graphics](https://openflux3.com/opus-5-5-video-generator): a separate scene-generation and render workflow, with operation-based credit reservations. - [Humanize AI](https://openflux3.com/humanize-ai): rewrite supplied text while reviewing meaning and facts yourself; no detector-bypass promise. - Sign in, supply the chosen mode's required inputs, review its quote, then create. Inspect results in Creation History before downloading or reusing them. - AI generation requires login and sufficient credits. The site applies purchase checks to designated generated-file downloads. Browser image operations require an account, upload and store inputs/results privately, and do not use AI generation credits. Some background operations download browser model resources; they are not a promise of fully offline or upload-free processing. - Free generation credits are not currently configured as an automatic signup grant. Review your actual balance and any eligibility conditions. ## Current generation configuration - Standard image/video generation and text/motion workflows: configured. - Checkout: enabled. - Configuration status does not prove provider balance, queue health or a successful render. Availability may change; models.md lists enabled integrations and supported controls. ## Browser image utilities - [Compress Image](https://openflux3.com/compress-image) - [Resize Image](https://openflux3.com/resize-image) - [Convert Image](https://openflux3.com/convert-image) - [Rotate Image](https://openflux3.com/rotate-image) - [Crop Image](https://openflux3.com/crop-image) - [Watermark Image](https://openflux3.com/watermark-image) - [Background Remover](https://openflux3.com/background-remover) - [Transparent Background](https://openflux3.com/transparent-background) - [White Background](https://openflux3.com/white-background) - [Change Background Color](https://openflux3.com/change-background-color) ## Discover tool and model pages These are discovery links, including alternative/keyword pages. They are not a count of independently connected generation models. Use models.md for actual enabled integrations. ### Trending - [Ming Xi Gold Wings](https://openflux3.com/trending/ming-xi-gold-wings) - [Bella Hadid Green Floral Wings](https://openflux3.com/trending/bella-hadid-green-floral-wings) - [Gigi Hadid Silver Fringe Wings](https://openflux3.com/trending/gigi-hadid-silver-fringe-wings) - [Anok Yai Pink Flower Petals](https://openflux3.com/trending/anok-yai-pink-flower-petals) - [Anok Yai White Feather Wings](https://openflux3.com/trending/anok-yai-white-feather-wings) - [Jasmine Tookes Magenta Fringe Wings](https://openflux3.com/trending/jasmine-tookes-magenta-fringe-wings) - [Kylie Jenner White Wings Fantasy Bra](https://openflux3.com/trending/kylie-jenner-white-wings-fantasy-bra) - [Bulin 47](https://openflux3.com/trending/bulin-47) - [Alors On Danse](https://openflux3.com/trending/alors-on-danse) - [Hotel Lobby](https://openflux3.com/hotel-lobby-ai) - [Rumpelstiltskin](https://openflux3.com/trending/rumpelstiltskin) - [Burning Bridges](https://openflux3.com/trending/burning-bridges) - [Zombie Couple](https://openflux3.com/trending/zombie-couple) - [Ozil Goal](https://openflux3.com/trending/ozil-goal) - [My Ride Is Here](https://openflux3.com/trending/my-ride-is-here) - [Smalltown Boy](https://openflux3.com/trending/smalltown-boy) - [Gas Station Dance](https://openflux3.com/trending/gas-station-dance) - [Coldplay Kiss Cam](https://openflux3.com/trending/coldplay-kiss-cam) - [Flying Car](https://openflux3.com/trending/flying-car) - [A2O LITE](https://openflux3.com/trending/a2o-lite) - [Enzo Fernandez](https://openflux3.com/trending/enzo-fernandez) - [Crazy Frog](https://openflux3.com/trending/crazy-frog) - [Bad Times](https://openflux3.com/trending/bad-times) ### Video Tools - [Loremotion AI](https://openflux3.com/loremotion-ai) - [Narrative AI Video Editor](https://openflux3.com/narrative-ai-video-editor) - [Raindance AI](https://openflux3.com/raindance-ai) - [EveryGen AI Video Generator](https://openflux3.com/everygen-ai-video-generator) - [AI Video Generator](https://openflux3.com/ai-video-generator) - [Text to Video](https://openflux3.com/text-to-video) - [Image to Video](https://openflux3.com/image-to-video) - [Video to Video](https://openflux3.com/video-to-video) - [AI Video Editor](https://openflux3.com/ai-video-editor) - [AI Video Extender](https://openflux3.com/ai-video-extender) - [AI Video Upscaler](https://openflux3.com/ai-video-upscaler) - [AI Video Background Remover](https://openflux3.com/ai-video-background-remover) - [AI Video Face Swap](https://openflux3.com/ai-video-face-swap) - [AI Lip Sync](https://openflux3.com/ai-lip-sync) - [AI Talking Photo](https://openflux3.com/ai-talking-photo) - [AI Dance Video Generator](https://openflux3.com/ai-dance-video-generator) - [AI Animation Generator](https://openflux3.com/ai-animation-generator) - [AI Anime Video Generator](https://openflux3.com/ai-anime-video-generator) - [AI Product Video Generator](https://openflux3.com/ai-product-video-generator) - [AI Video Ad Generator](https://openflux3.com/ai-video-ad-generator) - [AI UGC Video Generator](https://openflux3.com/ai-ugc-video-generator) - [AI Music Video Generator](https://openflux3.com/ai-music-video-generator) ### Video Models - [MiniMax H3 Max Turbo](https://openflux3.com/minimax-h3-max-turbo) - [MiniMax H3 Max](https://openflux3.com/minimax-h3-max) - [H3 Max Camera Control](https://openflux3.com/h3-max-camera-control) - [H3 Max Lip Sync](https://openflux3.com/h3-max-lip-sync) - [MiniMax H3](https://openflux3.com/minimax-h3) - [Hailuo 02 Pro](https://openflux3.com/hailuo-02-pro) - [Hailuo 02 Standard](https://openflux3.com/hailuo-02-standard) - [Hailuo 2.3 Pro](https://openflux3.com/hailuo-2-3-pro) - [Hailuo 2.3 Standard](https://openflux3.com/hailuo-2-3-standard) - [Opus 5.5 Video Generator](https://openflux3.com/opus-5-5-video-generator) - [H3 Max Styles](https://openflux3.com/h3-max-styles) - [LoRA](https://openflux3.com/lora) - [Seedance 2.5](https://openflux3.com/seedance-2-5) - [Seedance 2.0](https://openflux3.com/seedance-2-0) - [Seedance 2.0 Mini](https://openflux3.com/seedance-2-0-mini) - [Seedance 1.5 Pro](https://openflux3.com/seedance-1-5-pro) - [Seedance 1.0 Pro](https://openflux3.com/seedance-1-0-pro) - [Veo 3.1](https://openflux3.com/veo-3-1) - [Gemini Omni](https://openflux3.com/gemini-omni) - [Wan 2.7](https://openflux3.com/wan-2-7) - [Wan 2.6](https://openflux3.com/wan-2-6) - [Wan 2.5](https://openflux3.com/wan-2-5) - [Kling 3.0](https://openflux3.com/kling-3-0) - [Kling 2.6 Pro](https://openflux3.com/kling-2-6-pro) - [Grok Imagine 1.5](https://openflux3.com/grok-imagine-1-5) - [HappyHorse 1.1](https://openflux3.com/happyhorse-1-1) - [HappyHorse 1.0](https://openflux3.com/happyhorse-1-0) - [All Video Models](https://openflux3.com/ai-video-generator) ### Image Tools - [Text to Image](https://openflux3.com/text-to-image) - [Image to Image](https://openflux3.com/image-to-image) - [AI Object Remover](https://openflux3.com/ai-object-remover) - [AI Product Image Generator](https://openflux3.com/ai-product-image-generator) - [AI Product Photography](https://openflux3.com/ai-product-photography) - [AI Product Photo Generator](https://openflux3.com/ai-product-photo-generator) - [E-commerce Product Photos](https://openflux3.com/ecommerce-product-photo-generator) - [Product Photos for Shopify](https://openflux3.com/ai-product-photos-for-shopify) - [Product Photos for Amazon](https://openflux3.com/ai-product-photos-for-amazon) - [Product Background Generator](https://openflux3.com/product-background-generator) - [AI Photo Editor](https://openflux3.com/ai-photo-editor) - [AI Image Enhancer](https://openflux3.com/ai-image-enhancer) - [AI Background Remover](https://openflux3.com/ai-background-remover) - [AI Face Swap](https://openflux3.com/ai-face-swap) - [AI Headshot Generator](https://openflux3.com/ai-headshot-generator) - [AI Portrait Generator](https://openflux3.com/ai-portrait-generator) - [AI Avatar Generator](https://openflux3.com/ai-avatar-generator) - [AI Image Generator](https://openflux3.com/ai-image-generator) - [Compress Image](https://openflux3.com/compress-image) - [Resize Image](https://openflux3.com/resize-image) - [Convert Image](https://openflux3.com/convert-image) - [Rotate Image](https://openflux3.com/rotate-image) - [Crop Image](https://openflux3.com/crop-image) - [Watermark Image](https://openflux3.com/watermark-image) - [Background Remover](https://openflux3.com/background-remover) - [Transparent Background](https://openflux3.com/transparent-background) - [White Background](https://openflux3.com/white-background) - [Change Background Color](https://openflux3.com/change-background-color) ### Image Models - [All Image Models](https://openflux3.com/ai-image-generator) - [GPT Image 2.5](https://openflux3.com/gpt-image-2-5) - [GPT Image 2](https://openflux3.com/gpt-image-2) - [GPT Image 1.5](https://openflux3.com/gpt-image-1-5) - [Nano Banana 2](https://openflux3.com/nano-banana-2) - [Nano Banana 2 Lite](https://openflux3.com/nano-banana-2-lite) - [Nano Banana Pro](https://openflux3.com/nano-banana-pro) - [Seedream 5.0 Lite](https://openflux3.com/seedream-5-0-lite) - [Seedream 5.0 Pro](https://openflux3.com/seedream-5-0-pro) - [Seedream 4.5](https://openflux3.com/seedream-4-5) ### Creative - [Gamma AI Alternative](https://openflux3.com/gamma-ai-alternative) - [AI Baby Generator](https://openflux3.com/ai-baby-generator) - [Capafy AI Alternative](https://openflux3.com/capafy-ai-alternative) - [Arena AI Alternative](https://openflux3.com/arena-ai-alternative) - [Prompt Seen](https://openflux3.com/prompt-seen) - [Humanize AI](https://openflux3.com/humanize-ai) - [AI Twerk Video Generator](https://openflux3.com/ai-twerk-video-generator) - [Bigfoot Video Generator](https://openflux3.com/bigfoot-video-generator) - [Viblo AI Alternative](https://openflux3.com/viblo-ai-alternative) - [Flow AI Alternative](https://openflux3.com/flow-ai-alternative) - [Google Gemini AI Alternative](https://openflux3.com/google-gemini-ai-alternative) - [Pruna AI Generator](https://openflux3.com/pruna-ai-generator) - [Everygen AI Generator](https://openflux3.com/everygen-ai-generator) - [AI Anime Generator](https://openflux3.com/ai-anime-generator) - [AI Logo Generator](https://openflux3.com/ai-logo-generator) - [AI Sticker Generator](https://openflux3.com/ai-sticker-generator) - [AI Figure Generator](https://openflux3.com/ai-figure-generator) - [AI Fashion Generator](https://openflux3.com/ai-fashion-generator) - [AI Interior Design](https://openflux3.com/ai-interior-design-generator) - [AI Banner Generator](https://openflux3.com/ai-banner-generator) - [AI Ad Creative Generator](https://openflux3.com/ai-ad-creative-generator) - [AI Tattoo Generator](https://openflux3.com/ai-tattoo-generator) - [AI Meme Generator](https://openflux3.com/ai-meme-generator) - [AI QR Code Generator](https://openflux3.com/ai-qr-code-generator) - [AI Wallpaper Generator](https://openflux3.com/ai-wallpaper-generator) - [AI YouTube Thumbnail](https://openflux3.com/ai-youtube-thumbnail-generator) - [AI Social Media Posts](https://openflux3.com/ai-social-media-post-generator) - [AI Sketch to Image](https://openflux3.com/ai-sketch-to-image) - [AI Book Cover Generator](https://openflux3.com/ai-book-cover-generator) - [AI Icon Generator](https://openflux3.com/ai-icon-generator) - [AI Pixel Art Generator](https://openflux3.com/ai-pixel-art-generator) ## Help and source references - [Tutorials](https://openflux3.com/blog) - [Prompt examples](https://openflux3.com/minimax-h3-max-prompts) - [Purchase plans](https://openflux3.com/pricing) - [Privacy](https://openflux3.com/privacy-policy) · [Terms](https://openflux3.com/terms-of-service) · [Refund policy](https://openflux3.com/refund-policy) - Support: hi@openflux3.com - [llms.txt](https://openflux3.com/llms.txt) - [llms-full.txt](https://openflux3.com/llms-full.txt) - [pricing.md](https://openflux3.com/pricing.md) - [models.md](https://openflux3.com/models.md) These English canonical documents use public application configuration. They grant no API or private-media access. Effective service configuration is read on request; application catalog and quote-code changes take effect after deployment. --- # OpenFlux 3 — plans, credits and quotes Canonical purchase page: https://openflux3.com/pricing Currency: USD. These are base catalog charges from the purchase UI and checkout configuration, excluding applicable taxes and promotions. An annual charge is the total billed for the year. New annual purchases deliver 1/12 of the annual total each month for 12 months, beginning after payment. Each allocation expires at the end of its subscription month. Legacy upfront orders retain their original terms; existing subscriptions switch only at a renewal at least 30 days after account acknowledgement. Checkout is enabled. ## Subscription catalog | Plan | Monthly charge | Credits per monthly period | Total annual charge | Credits per annual period | | --- | --- | --- | --- | --- | | Lite | $29.90 | 600 | $179.00 | 7200 | | Standard | $49.90 | 1500 | $299.00 | 18000 | | Pro | $99.90 | 3600 | $599.00 | 43200 | | Max | $199.90 | 8000 | $1199.00 | 96000 | ## Trending face-swap templates Only the FaceSwap-cloned Trending catalog (including Hotel Lobby) costs 300 universal Credits per completed video, across every available format and full-length Bad Times. Other image, video and creative tools retain their own quotes. Source-preview-only templates cannot be generated. New MV tickets are no longer sold. Existing ticket balances keep their original validity and may be explicitly chosen instead of Credits: one successful video consumes one ticket; failure returns that ticket. Never charge both. Historical jobs retain their original reserved amount on settlement/refund. Existing paid checkout orders still reconcile, and ticket usage remains visible in account/admin records. Admin grants are not purchases or revenue. ## One-time packs | Pack | One-time charge | Credits | | --- | --- | --- | | Starter | $39.90 | 800 | | Value | $79.90 | 2000 | | Pro | $199.90 | 7500 | | Bulk | $999.90 | 50000 | | Mega | $2599.00 | 160000 | The Max plan quantity control scales the selected period's charge and credit grant together. Compare the selected quantity and whole-period charge at checkout; a monthly equivalent displayed for annual billing is not a monthly charge. ## Grant validity and settlement - Monthly grants: 30 days; annual allocations: paid annual period end; one-time packs: 365 days from grant. - Signup grant: no automatic welcome-credit grant currently enabled. - Purchasing credits and spending generation credits are separate. Select inputs and settings before comparing quotes; output count, duration, resolution, audio, references and image quality can change consumption. - Generation reserves credits before submission. Confirmed completion captures the applicable amount; confirmed failures release/refund the reserved generation credits. Pending or ambiguous jobs can remain reserved while their status is reconciled. - Refunding reserved credits is not a cash refund. Payment cancellation and monetary refunds follow https://openflux3.com/refund-policy. - Browser image tools use no generation credits, but still require login and account storage. Downloads subject to the purchase gate require a paid purchase. ## Enabled video integrations: sample quotes | Model | Credits | Settings and sample inputs | | --- | --- | --- | | Flux 3 Max | 43 | text; 5s output setting; 720p; 16:9; audio on; one output | | Flux 3 Video | 85 | text; 5s output setting; 720p; 16:9; audio on; one output | | Flux 3 Max Keyframes | 43 | reference; 5s output setting; 720p; 16:9; audio on; one output | | Flux 3 Keyframes | 85 | reference; 5s output setting; 720p; 16:9; audio on; one output | | Flux 3 Extend | 205 | reference; 5s output setting; 720p; 16:9; audio on; sample 5s source media; one output | | Claude Fable 5.2 | 117 | text; 10s output setting; 720p; 16:9; audio off; one output | | Claude Opus 5.5 | 59 | text; 10s output setting; 720p; 16:9; audio off; one output | | GPT-6 Astra Pro | 147 | text; 10s output setting; 720p; 16:9; audio off; one output | | Gemini 4 Hydrogen | 22 | text; 10s output setting; 720p; 16:9; audio off; one output | | Gemini 4 Carbon | 30 | text; 10s output setting; 720p; 16:9; audio off; one output | | Gemini 4 Argon | 30 | text; 10s output setting; 720p; 16:9; audio off; one output | | Gemma 4 31B | 2 | text; 10s output setting; 720p; 16:9; audio off; one output | | Kimi K3.1 Pro | 16 | text; 10s output setting; 720p; 16:9; audio off; one output | | DeepSeek V4 Pro 0423 | 9 | text; 10s output setting; 720p; 16:9; audio off; one output | | DeepSeek V4.1 Flash | 4 | text; 10s output setting; 720p; 16:9; audio off; one output | | Qwen4 Max | 17 | text; 10s output setting; 720p; 16:9; audio off; one output | | Nemotron 3.5 Super VL | 2 | text; 10s output setting; 720p; 16:9; audio off; one output | | Grok 4.7 | 23 | text; 10s output setting; 720p; 16:9; audio off; one output | | Muse Wonder | 59 | text; 10s output setting; 720p; 16:9; audio off; one output | | Muse Spark 1.3 | 15 | text; 10s output setting; 720p; 16:9; audio off; one output | | Muse Spark Open | 15 | text; 10s output setting; 720p; 16:9; audio off; one output | | GPT-6.1 Terra Pro | 15 | text; 10s output setting; 720p; 16:9; audio off; one output | | GPT-6.1 Sol Pro | 30 | text; 10s output setting; 720p; 16:9; audio off; one output | | MiniMax M3 | 4 | text; 10s output setting; 720p; 16:9; audio off; one output | | MiniMax H3 Max Turbo | 7 | text; 5s output setting; 480P; 16:9; audio on; one output | | MiniMax H3 | 130 | reference; 5s output setting; 2K; adaptive; audio off; one output | | H3 Max | 50 | text; 5s output setting; 768P; 16:9; audio on; one output | | Seedance 2.5 | 84 | reference; 4s output setting; 480p; adaptive; audio on; one output | | Seedance 2.0 Fast | 44 | reference; 4s output setting; 480p; adaptive; audio on; one output | | Seedance 2.0 Pro | 55 | reference; 4s output setting; 480p; adaptive; audio on; one output | | Seedance 2.0 Mini | 29 | reference; 4s output setting; 480p; adaptive; audio on; one output | | Seedance 1.5 Pro | 5 | text; 4s output setting; 480p; 16:9; audio off; one output | | Wan 2.7 | 50 | text; 5s output setting; 720p; 16:9; audio off; one output | | Wan 2.6 | 50 | text; 5s output setting; 720p; 16:9; audio off; one output | | Grok Imagine | 42 | text; 6s output setting; 720p; 16:9; audio off; one output | | Kling 3.0 | 26 | text; 3s output setting; 720p; 16:9; audio off; version standard; one output | | PixVerse Extend | 20 | reference; 5s output setting; 720p; adaptive; audio off; sample 5s source media; one output | | ByteDance Video Upscaler | 4 | reference; 5s output setting; 1080p; adaptive; audio off; sample 5s source media; one output | | Bria Video Background Removal | 70 | reference; 5s output setting; source; adaptive; audio off; sample 5s source media; one output | | PixVerse Person Swap | 20 | reference; 5s output setting; 720p; adaptive; audio off; sample 5s source media; one output | | Sync Lip Sync 2 | 25 | reference; 5s output setting; source; adaptive; audio off; sample 5s source media; one output | | Sync Talking Photo | 67 | reference; 5s output setting; source; adaptive; audio off; sample 5s source media; one output | | Hailuo 02 Pro | 48 | text; 6s output setting; 1080p; 16:9; audio off; one output | | Hailuo 02 Standard | 27 | text; 6s output setting; 768p; 16:9; audio off; one output | | Hailuo 2.3 Pro | 49 | text; 6s output setting; 1080p; 16:9; audio off; one output | | Hailuo 2.3 Standard | 28 | text; 6s output setting; 768p; 16:9; audio off; one output | | Seedance 1.0 Pro | 61 | text; 5s output setting; 1080p; 16:9; audio off; one output | | Wan 2.5 | 75 | text; 5s output setting; 1080p; 16:9; audio on; one output | | Kling 2.6 Pro | 70 | text; 5s output setting; 1080p; 16:9; audio on; one output | | Veo 3.1 | 320 | text; 8s output setting; 720p; 16:9; audio on; one output | | HappyHorse 1.0 | 140 | text; 5s output setting; 1080p; 16:9; audio off; one output | | HappyHorse 1.1 | 90 | text; 5s output setting; 1080p; 16:9; audio off; one output | | Grok Imagine 1.5 | 84 | text; 6s output setting; 720p; 16:9; audio on; one output | | H3 Max Styles | 40 | text; 5s output setting; 768P; 16:9; audio on; one output | | H3 Max Camera Control | 40 | image; 5s output setting; 768P; 16:9; audio off; one output | | H3 Max Lip Sync | 40 | reference; 5s output setting; 768P; adaptive; audio on; sample 5s source media; one output | | Gemini Omni | 100 | text; 8s output setting; 720p; 16:9; audio on; one output | | H3 LoRA | 38 | text; 5s output setting; 768P; 16:9; audio on; one output | These figures call the same credit quote function as generation. For processing models, 5-second source media is a pricing example; actual source length determines the quote. Required input media must still pass validation. ## Enabled image integrations: one-output quote examples | Model | Settings | Credits per image | | --- | --- | --- | | Flux 3 Image | 1K; 1:1; one output; no additional references | 5 | | GPT Image 2.6 Flare | 1K; 1:1; high quality; one output; no additional references | 6 | | GPT Image 2.6 Flare | 2K; 1:1; high quality; one output; no additional references | 12 | | GPT Image 2.6 Flare | 4K; 1:1; high quality; one output; no additional references | 19 | | GPT Image 2.6 Sunburst | 1K; 1:1; high quality; one output; no additional references | 6 | | GPT Image 2.6 Sunburst | 2K; 1:1; high quality; one output; no additional references | 12 | | GPT Image 2.6 Sunburst | 4K; 1:1; high quality; one output; no additional references | 19 | | Claude Fable 5.2 | 720p; 1:1; one output; no additional references | 117 | | Claude Fable 5.2 | 1080p; 1:1; one output; no additional references | 117 | | Claude Opus 5.5 | 720p; 1:1; one output; no additional references | 59 | | Claude Opus 5.5 | 1080p; 1:1; one output; no additional references | 59 | | GPT-6 Astra Pro | 720p; 1:1; one output; no additional references | 147 | | GPT-6 Astra Pro | 1080p; 1:1; one output; no additional references | 147 | | Gemini 4 Hydrogen | 720p; 1:1; one output; no additional references | 22 | | Gemini 4 Hydrogen | 1080p; 1:1; one output; no additional references | 22 | | Gemini 4 Carbon | 720p; 1:1; one output; no additional references | 30 | | Gemini 4 Carbon | 1080p; 1:1; one output; no additional references | 30 | | Gemini 4 Argon | 720p; 1:1; one output; no additional references | 30 | | Gemini 4 Argon | 1080p; 1:1; one output; no additional references | 30 | | Gemma 4 31B | 720p; 1:1; one output; no additional references | 2 | | Gemma 4 31B | 1080p; 1:1; one output; no additional references | 2 | | Kimi K3.1 Pro | 720p; 1:1; one output; no additional references | 16 | | Kimi K3.1 Pro | 1080p; 1:1; one output; no additional references | 16 | | DeepSeek V4 Pro 0423 | 720p; 1:1; one output; no additional references | 9 | | DeepSeek V4 Pro 0423 | 1080p; 1:1; one output; no additional references | 9 | | DeepSeek V4.1 Flash | 720p; 1:1; one output; no additional references | 4 | | DeepSeek V4.1 Flash | 1080p; 1:1; one output; no additional references | 4 | | Qwen4 Max | 720p; 1:1; one output; no additional references | 17 | | Qwen4 Max | 1080p; 1:1; one output; no additional references | 17 | | Nemotron 3.5 Super VL | 720p; 1:1; one output; no additional references | 2 | | Nemotron 3.5 Super VL | 1080p; 1:1; one output; no additional references | 2 | | Grok 4.7 | 720p; 1:1; one output; no additional references | 23 | | Grok 4.7 | 1080p; 1:1; one output; no additional references | 23 | | Muse Wonder | 720p; 1:1; one output; no additional references | 59 | | Muse Wonder | 1080p; 1:1; one output; no additional references | 59 | | Muse Spark 1.3 | 720p; 1:1; one output; no additional references | 15 | | Muse Spark 1.3 | 1080p; 1:1; one output; no additional references | 15 | | Muse Spark Open | 720p; 1:1; one output; no additional references | 15 | | Muse Spark Open | 1080p; 1:1; one output; no additional references | 15 | | GPT-6.1 Terra Pro | 720p; 1:1; one output; no additional references | 15 | | GPT-6.1 Terra Pro | 1080p; 1:1; one output; no additional references | 15 | | GPT-6.1 Sol Pro | 720p; 1:1; one output; no additional references | 30 | | GPT-6.1 Sol Pro | 1080p; 1:1; one output; no additional references | 30 | | MiniMax M3 | 720p; 1:1; one output; no additional references | 4 | | MiniMax M3 | 1080p; 1:1; one output; no additional references | 4 | | Seedream 5.0 Pro | 1K; 1:1; one output; no additional references | 7 | | Seedream 5.0 Pro | 2K; 1:1; one output; no additional references | 14 | | GPT Image 2.5 Flare | 1K; 1:1; high quality; one output; no additional references | 6 | | GPT Image 2.5 Flare | 2K; 1:1; high quality; one output; no additional references | 11 | | GPT Image 2.5 Flare | 4K; 1:1; high quality; one output; no additional references | 18 | | GPT Image 2.5 Sunburst | 1K; 1:1; high quality; one output; no additional references | 6 | | GPT Image 2.5 Sunburst | 2K; 1:1; high quality; one output; no additional references | 11 | | GPT Image 2.5 Sunburst | 4K; 1:1; high quality; one output; no additional references | 18 | | GPT Image 2 | 1K; 1:1; one output; no additional references | 19 | | GPT Image 2 | 2K; 1:1; one output; no additional references | 25 | | GPT Image 2 | 4K; 1:1; one output; no additional references | 38 | | Nano Banana 2 | 1K; 1:1; one output; no additional references | 8 | | Nano Banana 2 | 2K; 1:1; one output; no additional references | 12 | | Nano Banana 2 | 4K; 1:1; one output; no additional references | 16 | | Nano Banana Pro | 1K; 1:1; one output; no additional references | 15 | | Nano Banana Pro | 2K; 1:1; one output; no additional references | 15 | | Nano Banana Pro | 4K; 1:1; one output; no additional references | 30 | | Nano Banana | default; 1:1; one output; no additional references | 4 | | Seedream 5 Lite | 2K; 1:1; one output; no additional references | 4 | | Seedream 5 Lite | 3K; 1:1; one output; no additional references | 4 | | Seedream 4.5 | 2K; 1:1; one output; no additional references | 4 | | Seedream 4.5 | 4K; 1:1; one output; no additional references | 4 | | Seedream V4 | 1K; 1:1; one output; no additional references | 4 | | Seedream V4 | 2K; 1:1; one output; no additional references | 4 | | Seedream V4 | 4K; 1:1; one output; no additional references | 4 | | Bria RMBG 2.0 | original; 1:1; one output; no additional references | 4 | | Illusion Diffusion | 1K; 1:1; one output; no additional references | 4 | | Z-Image | default; 1:1; one output; no additional references | 4 | | Nano Banana 2 Lite | 1K; 1:1; one output; no additional references | 5 | | GPT Image 1.5 | 1K; 1:1; one output; no additional references | 14 | Image references, non-square sizes, custom dimensions, quality, GIF/SVG format selection, and output counts may change the quote. GPT Image 2.6 Flare/Sunburst is the default model for GIF (832×832, 4 frames) and SVG generation. Output estimates do not promise a fixed number of affordable images or identical results. ## Separate workflows - Layer decomposition: reserve up to 16 layers. Auto/1K/1.5K reserves 72 credits; 2K reserves 144. Final capture uses actual layers and excess reserved credits are returned. This is a layer-based operation, not an ordinary one-image quote. - Opus motion graphics: quoted per create/revision operation, with configured reservation ceiling 92 credits. The quote depends on the brief and existing scene; confirmed cost settles the operation and releases unused reservation. Video duration alone does not define its price. - Humanize AI: quoted per text rewrite from source-text size and the output allowance. A sample natural-tone rewrite of “Please rewrite this sentence.” reserves 3 credits through the same preparation function used for submission. Final cost receipt determines settlement; unused reservation is returned. Only end-user credit quotes are published here, not supplier costs or private endpoints. Always inspect the actual workspace quote and checkout for your selected inputs. --- # OpenFlux 3 — enabled models and workflow controls Workspaces: https://openflux3.com/ai-video-generator and https://openflux3.com/ai-image-generator Prices: https://openflux3.com/pricing.md This list combines the studio model catalog with effective generation-service configuration. Standard generation is configured. Configured access does not guarantee provider capacity, account balance or output quality. Marketing/alternative pages in llms.txt are discovery entries, not additional integrations. ## Video generation and processing (58 enabled catalog entries) ### Flux 3 Max - Public model ID: flux-3-max; provider label: Black Forest Labs; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 10000 characters. - Resolutions: 720p, 1080p, 2K, 4K. - Duration options, seconds: 5–20, step 1. - Aspect ratios by mode: text: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16; image: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image true; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 5s, 16:9, audio on. ### Flux 3 Video - Public model ID: flux-3-video; provider label: Black Forest Labs; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 10000 characters. - Resolutions: 720p, 1080p, 1440p, 2160p. - Duration options, seconds: 5–20, step 1. - Aspect ratios by mode: text: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16; image: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image true; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 5s, 16:9, audio on. ### Flux 3 Max Keyframes - Public model ID: flux-3-max-keyframes; provider label: Black Forest Labs; operation: generation. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 10000 characters. - Resolutions: 720p, 1080p, 2K, 4K. - Duration options, seconds: 5–20, step 1. - Aspect ratios by mode: reference: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16. - Upload limits by mode: reference: 10 images, 0 videos, 0 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image false; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 720p, 5s, 16:9, audio on. ### Flux 3 Keyframes - Public model ID: flux-3-keyframes; provider label: Black Forest Labs; operation: generation. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 10000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 5–20, step 1. - Aspect ratios by mode: reference: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16. - Upload limits by mode: reference: 10 images, 0 videos, 0 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 720p, 5s, 16:9, audio on. ### Flux 3 Extend - Public model ID: flux-3-extend; provider label: Black Forest Labs; operation: extend. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 10000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 5–20, step 1. - Aspect ratios by mode: reference: auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16. - Upload limits by mode: reference: 0 images, 1 videos, 0 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 720p, 5s, 16:9, audio on. ### Claude Fable 5.2 - Public model ID: llm-claude-fable-5-2; provider label: Anthropic; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Claude Opus 5.5 - Public model ID: llm-claude-opus-5-5; provider label: Anthropic; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### GPT-6 Astra Pro - Public model ID: llm-gpt-6-astra-pro; provider label: OpenAI; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Gemini 4 Hydrogen - Public model ID: llm-gemini-4-hydrogen; provider label: Google; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Gemini 4 Carbon - Public model ID: llm-gemini-4-carbon; provider label: Google; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Gemini 4 Argon - Public model ID: llm-gemini-4-argon; provider label: Google; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Gemma 4 31B - Public model ID: llm-gemma-4-31b-it; provider label: Google; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Kimi K3.1 Pro - Public model ID: llm-kimi-k3-1-pro; provider label: Moonshot AI; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### DeepSeek V4 Pro 0423 - Public model ID: llm-deepseek-v4-pro; provider label: DeepSeek; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### DeepSeek V4.1 Flash - Public model ID: llm-deepseek-v4-1-flash; provider label: DeepSeek; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Qwen4 Max - Public model ID: llm-qwen4-max; provider label: Alibaba; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Nemotron 3.5 Super VL - Public model ID: llm-nemotron-3-5-super-vl; provider label: NVIDIA; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Grok 4.7 - Public model ID: llm-grok-4-7; provider label: xAI; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Muse Wonder - Public model ID: llm-muse-wonder; provider label: Meta; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Muse Spark 1.3 - Public model ID: llm-muse-spark-1-3; provider label: Meta; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### Muse Spark Open - Public model ID: llm-muse-spark-open; provider label: Meta; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### GPT-6.1 Terra Pro - Public model ID: llm-gpt-6-1-terra-pro; provider label: OpenAI; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### GPT-6.1 Sol Pro - Public model ID: llm-gpt-6-1-sol-pro; provider label: OpenAI; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### MiniMax M3 - Public model ID: llm-minimax-m3; provider label: MiniMax; operation: generation. - Modes: text. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 6000 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 10, 15, 20, 30. - Aspect ratios by mode: text: 16:9, 9:16, 1:1. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 10s, 16:9, audio off. ### MiniMax H3 Max Turbo - Public model ID: minimax-h3-max-turbo; provider label: MiniMax; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 50000 characters. - Resolutions: 480P, 768P, 1080P. - Duration options, seconds: 5–15, step 1. - Aspect ratios by mode: text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: native synchronized audio; end image true; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 480P, 5s, 16:9, audio on. ### MiniMax H3 - Public model ID: minimax-h3; provider label: MiniMax; operation: generation. - Modes: reference, text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 7000 characters. - Resolutions: 2K. - Duration options, seconds: 5–15, step 1. - Aspect ratios by mode: reference: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: input-dependent; no ratio selector. - Upload limits by mode: reference: 9 images, 3 videos, 3 audio files, 12 total; text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image true; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 2K, 5s, adaptive, audio off. ### H3 Max - Public model ID: minimax-h3-max; provider label: MiniMax; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 20000 characters. - Resolutions: 480P, 768P. - Duration options, seconds: 5–15, step 1. - Aspect ratios by mode: text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: native synchronized audio; end image true; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 768P, 5s, 16:9, audio on. ### Seedance 2.5 - Public model ID: seedance-2.5; provider label: Seedance; operation: generation. - Modes: reference, text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 20000 characters. - Resolutions: 480P, 720P. - Duration options, seconds: 4–30, step 1. - Aspect ratios by mode: reference: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; text: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; image: input-dependent; no ratio selector. - Upload limits by mode: reference: 30 images, 10 videos, 10 audio files, 50 total; text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image true; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 480p, 4s, adaptive, audio on. ### Seedance 2.0 Fast - Public model ID: seedance-2.0-fast; provider label: Seedance; operation: generation. - Modes: reference, text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 20000 characters. - Resolutions: 480P, 720P. - Duration options, seconds: 4–15, step 1. - Aspect ratios by mode: reference: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; text: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; image: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9. - Upload limits by mode: reference: 9 images, 3 videos, 3 audio files, 12 total; text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image true; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 480p, 4s, adaptive, audio on. ### Seedance 2.0 Pro - Public model ID: seedance-2.0-pro; provider label: Seedance; operation: generation. - Modes: reference, text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 20000 characters. - Resolutions: 480P, 720P, 1080P, 4K. - Duration options, seconds: 4–15, step 1. - Aspect ratios by mode: reference: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; text: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; image: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9. - Upload limits by mode: reference: 9 images, 3 videos, 3 audio files, 12 total; text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image true; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 480p, 4s, adaptive, audio on. ### Seedance 2.0 Mini - Public model ID: seedance-2.0-mini; provider label: Seedance; operation: generation. - Modes: reference, text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 20000 characters. - Resolutions: 480P, 720P. - Duration options, seconds: 4–15, step 1. - Aspect ratios by mode: reference: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; text: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; image: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9. - Upload limits by mode: reference: 9 images, 3 videos, 3 audio files, 12 total; text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image true; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 480p, 4s, adaptive, audio on. ### Seedance 1.5 Pro - Public model ID: seedance-1.5-pro; provider label: Seedance; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 20000 characters. - Resolutions: 480P, 720P, 1080P. - Duration options, seconds: 4, 8, 12. - Aspect ratios by mode: text: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9; image: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image true; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 480p, 4s, 16:9, audio off. ### Wan 2.7 - Public model ID: wan-2.7; provider label: Wan; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 5000 characters. - Resolutions: 720P, 1080P. - Duration options, seconds: 2–15, step 1. - Aspect ratios by mode: text: 16:9, 9:16, 1:1, 4:3, 3:4; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image true; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 5s, 16:9, audio off. ### Wan 2.6 - Public model ID: wan-2.6; provider label: Wan; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 1500 characters. - Resolutions: 720P, 1080P. - Duration options, seconds: 5, 10, 15. - Aspect ratios by mode: text: input-dependent; no ratio selector; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 5s, 16:9, audio off. ### Grok Imagine - Public model ID: grok-imagine; provider label: Grok; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 5000 characters. - Resolutions: 720P. - Duration options, seconds: 6, 10. - Aspect ratios by mode: text: 16:9, 9:16, 1:1, 3:2, 2:3; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: normal, fun, spicy; output formats: see result and workspace. - Defaults: text, 720p, 6s, 16:9, audio off. ### Kling 3.0 - Public model ID: kling-3.0; provider label: Kling; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2500 characters. - Resolutions: 720P. - Duration options, seconds: 3–15, step 1. - Aspect ratios by mode: text: 16:9, 9:16, 1:1; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image true; seed false; web search false; last-frame return false. - Versions: Std, Pro; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 3s, 16:9, audio off. ### PixVerse Extend - Public model ID: pixverse-extend; provider label: PixVerse; operation: extend. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2000 characters. - Resolutions: 360P, 540P, 720P, 1080P. - Duration options, seconds: 5. - Aspect ratios by mode: reference: input-dependent; no ratio selector. - Upload limits by mode: reference: 0 images, 1 videos, 0 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 720p, 5s, adaptive, audio off. ### ByteDance Video Upscaler - Public model ID: bytedance-video-upscaler; provider label: ByteDance; operation: upscale. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: optional; maximum 2000 characters. - Resolutions: 1080P, 2K, 4K. - Duration options, seconds: 5. - Aspect ratios by mode: reference: input-dependent; no ratio selector. - Upload limits by mode: reference: 0 images, 1 videos, 0 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 1080p, 5s, adaptive, audio off. ### Bria Video Background Removal - Public model ID: bria-video-background; provider label: Bria; operation: remove-background. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: optional; maximum 2000 characters. - Resolutions: Source. - Duration options, seconds: 5. - Aspect ratios by mode: reference: input-dependent; no ratio selector. - Upload limits by mode: reference: 0 images, 1 videos, 0 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, source, 5s, adaptive, audio off. ### PixVerse Person Swap - Public model ID: pixverse-swap; provider label: PixVerse; operation: swap. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: optional; maximum 2000 characters. - Resolutions: 360P, 540P, 720P. - Duration options, seconds: 5. - Aspect ratios by mode: reference: input-dependent; no ratio selector. - Upload limits by mode: reference: 1 images, 1 videos, 0 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 720p, 5s, adaptive, audio off. ### Sync Lip Sync 2 - Public model ID: sync-lipsync-2; provider label: Sync; operation: lipsync. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: optional; maximum 2000 characters. - Resolutions: Source. - Duration options, seconds: 5. - Aspect ratios by mode: reference: input-dependent; no ratio selector. - Upload limits by mode: reference: 0 images, 1 videos, 1 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, source, 5s, adaptive, audio off. ### Sync Talking Photo - Public model ID: sync-talking-photo; provider label: Sync; operation: talking-photo. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: optional; maximum 2000 characters. - Resolutions: Source. - Duration options, seconds: 5. - Aspect ratios by mode: reference: input-dependent; no ratio selector. - Upload limits by mode: reference: 1 images, 0 videos, 1 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, source, 5s, adaptive, audio off. ### Hailuo 02 Pro - Public model ID: hailuo-02-pro; provider label: MiniMax; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2000 characters. - Resolutions: 1080p. - Duration options, seconds: 6. - Aspect ratios by mode: text: input-dependent; no ratio selector; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image true; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 1080p, 6s, 16:9, audio off. ### Hailuo 02 Standard - Public model ID: hailuo-02-standard; provider label: MiniMax; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2000 characters. - Resolutions: 768p. - Duration options, seconds: 6, 10. - Aspect ratios by mode: text: input-dependent; no ratio selector; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image true; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 768p, 6s, 16:9, audio off. ### Hailuo 2.3 Pro - Public model ID: hailuo-2.3-pro; provider label: MiniMax; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2000 characters. - Resolutions: 1080p. - Duration options, seconds: 6. - Aspect ratios by mode: text: input-dependent; no ratio selector; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 1080p, 6s, 16:9, audio off. ### Hailuo 2.3 Standard - Public model ID: hailuo-2.3-standard; provider label: MiniMax; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2000 characters. - Resolutions: 768p. - Duration options, seconds: 6, 10. - Aspect ratios by mode: text: input-dependent; no ratio selector; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 768p, 6s, 16:9, audio off. ### Seedance 1.0 Pro - Public model ID: seedance-1.0-pro; provider label: Seedance; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2000 characters. - Resolutions: 480p, 720p, 1080p. - Duration options, seconds: 2–12, step 1. - Aspect ratios by mode: text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image true; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 1080p, 5s, 16:9, audio off. ### Wan 2.5 - Public model ID: wan-2.5; provider label: Wan; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 1500 characters. - Resolutions: 480p, 720p, 1080p. - Duration options, seconds: 5, 10. - Aspect ratios by mode: text: 16:9, 9:16, 1:1; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 1 audio files, 1 total; image: 1 images, 0 videos, 1 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: native synchronized audio; end image false; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 1080p, 5s, 16:9, audio on. ### Kling 2.6 Pro - Public model ID: kling-2.6-pro; provider label: Kling; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2500 characters. - Resolutions: 1080p. - Duration options, seconds: 5, 10. - Aspect ratios by mode: text: 16:9, 9:16, 1:1; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image true; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 1080p, 5s, 16:9, audio on. ### Veo 3.1 - Public model ID: veo-3.1; provider label: Google; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 20000 characters. - Resolutions: 720p, 1080p, 4k. - Duration options, seconds: 4, 6, 8. - Aspect ratios by mode: text: 16:9, 9:16; image: auto, 16:9, 9:16. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: optional audio setting; end image false; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 8s, 16:9, audio on. ### HappyHorse 1.0 - Public model ID: happyhorse-1.0; provider label: Alibaba; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2500 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 3–15, step 1. - Aspect ratios by mode: text: 16:9, 9:16, 1:1, 4:3, 3:4; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 1080p, 5s, 16:9, audio off. ### HappyHorse 1.1 - Public model ID: happyhorse-1.1; provider label: Alibaba; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 2500 characters. - Resolutions: 720p, 1080p. - Duration options, seconds: 3–15, step 1. - Aspect ratios by mode: text: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 1080p, 5s, 16:9, audio off. ### Grok Imagine 1.5 - Public model ID: grok-imagine-1.5; provider label: Grok; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 4096 characters. - Resolutions: 480p, 720p, 1080p. - Duration options, seconds: 1–15, step 1. - Aspect ratios by mode: text: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: native synchronized audio; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 6s, 16:9, audio on. ### H3 Max Styles - Public model ID: h3-max-styles; provider label: MiniMax; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 49868 characters. - Resolutions: 768P. - Duration options, seconds: 5–15, step 1. - Aspect ratios by mode: text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: native synchronized audio; end image false; seed true; web search false; last-frame return false. - Versions: no version selector; styles: Hand drawn, VHS, Retro toon, Low poly, 16-bit pixel; output formats: see result and workspace. - Defaults: text, 768P, 5s, 16:9, audio on. ### H3 Max Camera Control - Public model ID: h3-max-camera-control; provider label: MiniMax; operation: generation. - Modes: image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: optional; maximum 50000 characters. - Resolutions: 480P, 768P, 1080P. - Duration options, seconds: 3–15, step 1. - Aspect ratios by mode: image: input-dependent; no ratio selector. - Upload limits by mode: image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: no optional audio setting advertised; end image false; seed true; web search false; last-frame return false. - Versions: no version selector; styles: Orbit right, Orbit left, Push in, Pull back, Crane up; output formats: see result and workspace. - Defaults: image, 768P, 5s, 16:9, audio off. ### H3 Max Lip Sync - Public model ID: h3-max-lip-sync; provider label: MiniMax; operation: h3-lipsync. - Modes: reference. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: optional; maximum 2000 characters. - Resolutions: 480P, 768P, 1080P, 2K. - Duration options, seconds: 5. - Aspect ratios by mode: reference: input-dependent; no ratio selector. - Upload limits by mode: reference: 1 images, 0 videos, 1 audio files, 12 total. These are maxima, not a guarantee that every combination is accepted. - Audio: native synchronized audio; end image false; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: reference, 768P, 5s, adaptive, audio on. ### Gemini Omni - Public model ID: gemini-omni; provider label: Google; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 20000 characters. - Resolutions: 720p. - Duration options, seconds: 3–10, step 1. - Aspect ratios by mode: text: 16:9, 9:16; image: 16:9, 9:16. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 1 images, 0 videos, 0 audio files, 1 total. These are maxima, not a guarantee that every combination is accepted. - Audio: native synchronized audio; end image false; seed false; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 720p, 8s, 16:9, audio on. ### H3 LoRA - Public model ID: h3-lora; provider label: MiniMax; operation: generation. - Modes: text, image. Text mode uses a prompt; image mode needs an image; reference/processing modes need their source media. - Prompt: required; maximum 50000 characters. - Resolutions: 480P, 768P, 2K, 4K. - Duration options, seconds: 5–15, step 1. - Aspect ratios by mode: text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: input-dependent; no ratio selector. - Upload limits by mode: text: 0 images, 0 videos, 0 audio files, 0 total; image: 2 images, 0 videos, 0 audio files, 2 total. These are maxima, not a guarantee that every combination is accepted. - Audio: native synchronized audio; end image true; seed true; web search false; last-frame return false. - Versions: no version selector; styles: no style selector; output formats: see result and workspace. - Defaults: text, 768P, 5s, 16:9, audio on. - LoRA inference accepts an authorized LoRA URL or repository and strength. This is not a hosted model-training service. ## Images (37 enabled catalog entries) ### Flux 3 Image - Public model ID: flux-3-image; provider label: Black Forest Labs. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 10000 characters. - Resolutions: 1K; declared default resolution: 1K. - Aspect ratios: auto, 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2. - Reference limit: 10; MIME types: image/jpeg, image/png, image/webp; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: jpeg. ### GPT Image 2.6 Flare - Public model ID: gpt-image-2.6-flare; provider label: OpenAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 32000 characters. - Resolutions: 1K, 2K, 4K; declared default resolution: 1K. - Aspect ratios: 1:1, auto, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5. - Reference limit: 16; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–10; declared output format: see workspace. - Additional public controls: {"quality":{"values":["auto","low","medium","high","xhigh","max"],"default":"high"},"background":{"values":["auto","transparent","opaque"],"default":"auto"},"outputFormat":{"values":["png","jpeg","webp"],"default":"png"},"imageSize":{"presets":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9"],"multiple":16,"maxEdge":3840,"minPixels":655360,"maxPixels":8294400,"maxAspectRatio":3},"outputs":{"min":1,"max":10,"default":1},"optionalMask":true}. ### GPT Image 2.6 Sunburst - Public model ID: gpt-image-2.6-sunburst; provider label: OpenAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 32000 characters. - Resolutions: 1K, 2K, 4K; declared default resolution: 1K. - Aspect ratios: 1:1, auto, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5. - Reference limit: 16; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–10; declared output format: see workspace. - Additional public controls: {"quality":{"values":["auto","low","medium","high","xhigh","max"],"default":"high"},"background":{"values":["auto","transparent","opaque"],"default":"auto"},"outputFormat":{"values":["png","jpeg","webp"],"default":"png"},"imageSize":{"presets":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9"],"multiple":16,"maxEdge":3840,"minPixels":655360,"maxPixels":8294400,"maxAspectRatio":3},"outputs":{"min":1,"max":10,"default":1},"optionalMask":true}. ### Claude Fable 5.2 - Public model ID: llm-claude-fable-5-2; provider label: Anthropic. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Claude Opus 5.5 - Public model ID: llm-claude-opus-5-5; provider label: Anthropic. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### GPT-6 Astra Pro - Public model ID: llm-gpt-6-astra-pro; provider label: OpenAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Gemini 4 Hydrogen - Public model ID: llm-gemini-4-hydrogen; provider label: Google. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Gemini 4 Carbon - Public model ID: llm-gemini-4-carbon; provider label: Google. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Gemini 4 Argon - Public model ID: llm-gemini-4-argon; provider label: Google. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Gemma 4 31B - Public model ID: llm-gemma-4-31b-it; provider label: Google. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Kimi K3.1 Pro - Public model ID: llm-kimi-k3-1-pro; provider label: Moonshot AI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### DeepSeek V4 Pro 0423 - Public model ID: llm-deepseek-v4-pro; provider label: DeepSeek. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### DeepSeek V4.1 Flash - Public model ID: llm-deepseek-v4-1-flash; provider label: DeepSeek. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Qwen4 Max - Public model ID: llm-qwen4-max; provider label: Alibaba. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Nemotron 3.5 Super VL - Public model ID: llm-nemotron-3-5-super-vl; provider label: NVIDIA. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Grok 4.7 - Public model ID: llm-grok-4-7; provider label: xAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Muse Wonder - Public model ID: llm-muse-wonder; provider label: Meta. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Muse Spark 1.3 - Public model ID: llm-muse-spark-1-3; provider label: Meta. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Muse Spark Open - Public model ID: llm-muse-spark-open; provider label: Meta. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### GPT-6.1 Terra Pro - Public model ID: llm-gpt-6-1-terra-pro; provider label: OpenAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### GPT-6.1 Sol Pro - Public model ID: llm-gpt-6-1-sol-pro; provider label: OpenAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### MiniMax M3 - Public model ID: llm-minimax-m3; provider label: MiniMax. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 6000 characters. - Resolutions: 720p, 1080p; declared default resolution: 720p. - Aspect ratios: 16:9, 9:16, 1:1. - Reference limit: 4; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: png. ### Seedream 5.0 Pro - Public model ID: seedream-5-pro; provider label: Seedream. - Modes: layer-decomposition, text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 5000 characters. - Resolutions: 1K, 2K; declared default resolution: 2K. - Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3. - Reference limit: 10; MIME types: see uploader; maximum bytes per reference: 31457280. - Outputs: 1–6; declared output format: see workspace. - Layer resolutions: auto, 1K, 1.5K, 2K; MIME types: image/jpeg, image/png, image/webp, image/bmp, image/tiff, image/gif. ### GPT Image 2.5 Flare - Public model ID: gpt-image-2.5-flare; provider label: OpenAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 32000 characters. - Resolutions: 1K, 2K, 4K; declared default resolution: 1K. - Aspect ratios: 1:1, auto, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5. - Reference limit: 16; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–10; declared output format: see workspace. - Additional public controls: {"quality":{"values":["auto","low","medium","high","xhigh","max"],"default":"high"},"background":{"values":["auto","transparent","opaque"],"default":"auto"},"outputFormat":{"values":["png","jpeg","webp"],"default":"png"},"imageSize":{"presets":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9"],"multiple":16,"maxEdge":3840,"minPixels":655360,"maxPixels":8294400,"maxAspectRatio":3},"outputs":{"min":1,"max":10,"default":1},"optionalMask":true}. ### GPT Image 2.5 Sunburst - Public model ID: gpt-image-2.5-sunburst; provider label: OpenAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 32000 characters. - Resolutions: 1K, 2K, 4K; declared default resolution: 1K. - Aspect ratios: 1:1, auto, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5. - Reference limit: 16; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–10; declared output format: see workspace. - Additional public controls: {"quality":{"values":["auto","low","medium","high","xhigh","max"],"default":"high"},"background":{"values":["auto","transparent","opaque"],"default":"auto"},"outputFormat":{"values":["png","jpeg","webp"],"default":"png"},"imageSize":{"presets":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9"],"multiple":16,"maxEdge":3840,"minPixels":655360,"maxPixels":8294400,"maxAspectRatio":3},"outputs":{"min":1,"max":10,"default":1},"optionalMask":true}. ### GPT Image 2 - Public model ID: gpt-image-2; provider label: OpenAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 20000 characters. - Resolutions: 1K, 2K, 4K; declared default resolution: 1K. - Aspect ratios: auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5. - Reference limit: 16; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–4; declared output format: see workspace. ### Nano Banana 2 - Public model ID: nano-banana-2; provider label: Nano Banana. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 20000 characters. - Resolutions: 1K, 2K, 4K; declared default resolution: see workspace selection. - Aspect ratios: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. - Reference limit: 14; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–4; declared output format: see workspace. ### Nano Banana Pro - Public model ID: nano-banana-pro; provider label: Nano Banana. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 20000 characters. - Resolutions: 1K, 2K, 4K; declared default resolution: see workspace selection. - Aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. - Reference limit: 14; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–4; declared output format: see workspace. ### Nano Banana - Public model ID: nano-banana; provider label: Nano Banana. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 20000 characters. - Resolutions: model default; declared default resolution: see workspace selection. - Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9. - Reference limit: 10; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–4; declared output format: see workspace. ### Seedream 5 Lite - Public model ID: seedream-5-lite; provider label: Seedream. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 5000 characters. - Resolutions: 2K, 3K; declared default resolution: see workspace selection. - Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9. - Reference limit: 10; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–4; declared output format: see workspace. ### Seedream 4.5 - Public model ID: seedream-4-5; provider label: Seedream. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 3000 characters. - Resolutions: 2K, 4K; declared default resolution: see workspace selection. - Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9. - Reference limit: 10; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–4; declared output format: see workspace. ### Seedream V4 - Public model ID: seedream-v4; provider label: Seedream. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 5000 characters. - Resolutions: 1K, 2K, 4K; declared default resolution: see workspace selection. - Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9. - Reference limit: 10; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–4; declared output format: see workspace. ### Bria RMBG 2.0 - Public model ID: bria-background-remove; provider label: Bria. - Modes: image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: optional, maximum 0 characters. - Resolutions: original; declared default resolution: original. - Aspect ratios: auto. - Reference limit: 1; MIME types: image/jpeg, image/png, image/webp; maximum bytes per reference: 31457280. - Outputs: 1; declared output format: png. ### Illusion Diffusion - Public model ID: illusion-diffusion; provider label: Illusion Diffusion. - Modes: image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 2000 characters. - Resolutions: 1K; declared default resolution: 1K. - Aspect ratios: 1:1. - Reference limit: 1; MIME types: image/jpeg, image/png, image/webp; maximum bytes per reference: 10485760. - Outputs: 1; declared output format: png. ### Z-Image - Public model ID: z-image; provider label: Z-Image. - Modes: text. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 1000 characters. - Resolutions: model default; declared default resolution: see workspace selection. - Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16. - Reference limit: 0; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1; declared output format: see workspace. ### Nano Banana 2 Lite - Public model ID: nano-banana-2-lite; provider label: Nano Banana. - Modes: text. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 50000 characters. - Resolutions: 1K; declared default resolution: 1K. - Aspect ratios: auto, 1:1, 21:9, 16:9, 3:2, 4:3, 5:4, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8. - Reference limit: 0; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–4; declared output format: png. ### GPT Image 1.5 - Public model ID: gpt-image-1.5; provider label: OpenAI. - Modes: text, image. Text mode accepts a prompt without references; image mode requires at least one supported reference. Layer decomposition requires a source image and follows its own settings. - Prompt: required, maximum 32000 characters. - Resolutions: 1K; declared default resolution: 1K. - Aspect ratios: 1:1, 3:2, 2:3. - Reference limit: 10; MIME types: see uploader; maximum bytes per reference: see uploader. - Outputs: 1–4; declared output format: png. ## Other workflows ### Opus 5.5 · Motion Graphics - Public workflow ID: claude-opus-5-5-motion; page: https://openflux3.com/opus-5-5-video-generator. - Creates or revises structured motion graphics and renders a video. It is separate from photorealistic provider-video generation. - Prompt limit: 6000; up to 4 image elements; durations: 10, 15, 20, 30 seconds; resolutions: 720p, 1080p; ratios: 16:9, 9:16, 1:1; styles: Sketch, Motion. - Defaults: 20s, 720p, 16:9, audio off. No native audio generation in this workflow. Quoted per operation, not per second. ### Humanize AI - Page: https://openflux3.com/humanize-ai; configured model: google/gemini-2.5-flash. - Input: original text up to 12000 characters; tones: natural, friendly, professional; output: rewritten text. Natural tone is the initial choice. - Review factual meaning, names and numbers. No detection-score or publication guarantee. Reservation and actual-cost settlement are documented in pricing.md. Browser image tools are listed in llms.txt and do not represent paid cloud generation models. Login and mode-specific validation still apply. Provider URLs, payment identifiers, API keys, user data and private media are excluded from these documents.