# Flux 3 Tools — AI video and image tools

> Flux 3 Tools (https://flux3.tools) is an independent creative website for AI video generation, image generation and editing. It is not the official website of Black Forest Labs, MiniMax or fal.

## Start creating
- [Flux 3 Video](https://flux3.tools/flux-3-video): text or one opening frame at 720p–2160p; optional end frame at 720p / 1080p; 5–20 seconds; optional synchronized audio.
- The same workspace also offers Flux 3 Keyframes (1–10 images at unique 24 fps frame indices) and Flux 3 Extend (one MP4 under 50 MB and under 15 seconds). Both create 5–20 whole seconds at 720p / 1080p with optional audio. Paid output from these flows has not yet been verified on this site.
- [Flux 3 Image](https://flux3.tools/flux-3-image): text generation or up to ten image references; currently 1K, one output per request. Higher image tiers remain unavailable while their partner pricing is verified.
- [AI Video](https://flux3.tools/ai-video-generator): choose a model, text/image/reference mode, supported settings and a credit quote.
- [AI Image](https://flux3.tools/ai-image-generator): generate from text or edit reference images with the chosen model.
- Choose a tool or model, prepare its required inputs, review the Create quote, sign in and create. Use Creation History to review results.
- Browsing does not automatically open purchase dialogs. Generation requires login and sufficient credits; designated generated-file downloads require a previous paid purchase. Buying credits does not remove per-generation credit charges.
- Browser image tools operate locally without generation credits. Some background tools may download browser model resources. AI tools require server processing and credits.
- Preset and example reuse prepares a draft; it does not submit a generation by itself.
- Model settings and limits differ. A tool/alternative landing page is not a separate provider integration or an affiliation with the named brand.
- Opus 5.5 Video Generator is a separate motion-graphics workflow; its separate settings and credit reservation are documented in models.md and pricing.md.

## Browser image tools
- [Compress Image](https://flux3.tools/compress-image)
- [Resize Image](https://flux3.tools/resize-image)
- [Convert Image](https://flux3.tools/convert-image)
- [Rotate Image](https://flux3.tools/rotate-image)
- [Crop Image](https://flux3.tools/crop-image)
- [Watermark Image](https://flux3.tools/watermark-image)
- [Background Remover](https://flux3.tools/background-remover)
- [Transparent Background](https://flux3.tools/transparent-background)
- [White Background](https://flux3.tools/white-background)
- [Change Background Color](https://flux3.tools/change-background-color)

## Tool and model page index
### Video Tools
- [Flux 3 Video](https://flux3.tools/flux-3-video)
- [AI Video Generator](https://flux3.tools/ai-video-generator)
- [Text to Video](https://flux3.tools/text-to-video)
- [Image to Video](https://flux3.tools/image-to-video)
- [Video to Video](https://flux3.tools/video-to-video)
- [AI Video Editor](https://flux3.tools/ai-video-editor)
- [AI Video Extender](https://flux3.tools/ai-video-extender)
- [AI Video Upscaler](https://flux3.tools/ai-video-upscaler)
- [AI Video Background Remover](https://flux3.tools/ai-video-background-remover)
- [AI Video Face Swap](https://flux3.tools/ai-video-face-swap)
- [AI Lip Sync](https://flux3.tools/ai-lip-sync)
- [AI Talking Photo](https://flux3.tools/ai-talking-photo)
- [AI Dance Video Generator](https://flux3.tools/ai-dance-video-generator)
- [AI Animation Generator](https://flux3.tools/ai-animation-generator)
- [AI Anime Video Generator](https://flux3.tools/ai-anime-video-generator)
- [AI Product Video Generator](https://flux3.tools/ai-product-video-generator)
- [AI Video Ad Generator](https://flux3.tools/ai-video-ad-generator)
- [AI UGC Video Generator](https://flux3.tools/ai-ugc-video-generator)
- [AI Music Video Generator](https://flux3.tools/ai-music-video-generator)

### Video Models
- [Opus 5.5 Video Generator](https://flux3.tools/opus-5-5-video-generator)
- [MiniMax H3 Max Turbo](https://flux3.tools/minimax-h3-max-turbo)
- [MiniMax H3 Max](https://flux3.tools/minimax-h3-max)
- [H3 Max Camera Control](https://flux3.tools/h3-max-camera-control)
- [H3 Max Lip Sync](https://flux3.tools/h3-max-lip-sync)
- [MiniMax H3](https://flux3.tools/minimax-h3)
- [Hailuo 02 Pro](https://flux3.tools/hailuo-02-pro)
- [Hailuo 02 Standard](https://flux3.tools/hailuo-02-standard)
- [Hailuo 2.3 Pro](https://flux3.tools/hailuo-2-3-pro)
- [Hailuo 2.3 Standard](https://flux3.tools/hailuo-2-3-standard)
- [H3 Max Styles](https://flux3.tools/h3-max-styles)
- [LoRA](https://flux3.tools/lora)
- [Seedance 2.5](https://flux3.tools/seedance-2-5)
- [Seedance 2.0](https://flux3.tools/seedance-2-0)
- [Seedance 2.0 Mini](https://flux3.tools/seedance-2-0-mini)
- [Seedance 1.5 Pro](https://flux3.tools/seedance-1-5-pro)
- [Seedance 1.0 Pro](https://flux3.tools/seedance-1-0-pro)
- [Veo 3.1](https://flux3.tools/veo-3-1)
- [Gemini Omni](https://flux3.tools/gemini-omni)
- [Wan 2.7](https://flux3.tools/wan-2-7)
- [Wan 2.6](https://flux3.tools/wan-2-6)
- [Wan 2.5](https://flux3.tools/wan-2-5)
- [Kling 3.0](https://flux3.tools/kling-3-0)
- [Kling 2.6 Pro](https://flux3.tools/kling-2-6-pro)
- [Grok Imagine 1.5](https://flux3.tools/grok-imagine-1-5)
- [HappyHorse 1.1](https://flux3.tools/happyhorse-1-1)
- [HappyHorse 1.0](https://flux3.tools/happyhorse-1-0)
- [All Video Models](https://flux3.tools/ai-video-generator)

### Image Tools
- [Flux 3 Image](https://flux3.tools/flux-3-image)
- [Text to Image](https://flux3.tools/text-to-image)
- [Image to Image](https://flux3.tools/image-to-image)
- [AI Object Remover](https://flux3.tools/ai-object-remover)
- [AI Product Image Generator](https://flux3.tools/ai-product-image-generator)
- [AI Product Photography](https://flux3.tools/ai-product-photography)
- [AI Product Photo Generator](https://flux3.tools/ai-product-photo-generator)
- [E-commerce Product Photos](https://flux3.tools/ecommerce-product-photo-generator)
- [Product Photos for Shopify](https://flux3.tools/ai-product-photos-for-shopify)
- [Product Photos for Amazon](https://flux3.tools/ai-product-photos-for-amazon)
- [Product Background Generator](https://flux3.tools/product-background-generator)
- [AI Photo Editor](https://flux3.tools/ai-photo-editor)
- [AI Image Enhancer](https://flux3.tools/ai-image-enhancer)
- [AI Background Remover](https://flux3.tools/ai-background-remover)
- [AI Face Swap](https://flux3.tools/ai-face-swap)
- [AI Headshot Generator](https://flux3.tools/ai-headshot-generator)
- [AI Portrait Generator](https://flux3.tools/ai-portrait-generator)
- [AI Avatar Generator](https://flux3.tools/ai-avatar-generator)
- [AI Image Generator](https://flux3.tools/ai-image-generator)
- [Compress Image](https://flux3.tools/compress-image)
- [Resize Image](https://flux3.tools/resize-image)
- [Convert Image](https://flux3.tools/convert-image)
- [Rotate Image](https://flux3.tools/rotate-image)
- [Crop Image](https://flux3.tools/crop-image)
- [Watermark Image](https://flux3.tools/watermark-image)
- [Background Remover](https://flux3.tools/background-remover)
- [Transparent Background](https://flux3.tools/transparent-background)
- [White Background](https://flux3.tools/white-background)
- [Change Background Color](https://flux3.tools/change-background-color)

### Image Models
- [All Image Models](https://flux3.tools/ai-image-generator)
- [GPT Image 2.5](https://flux3.tools/gpt-image-2-5)
- [GPT Image 2](https://flux3.tools/gpt-image-2)
- [GPT Image 1.5](https://flux3.tools/gpt-image-1-5)
- [Nano Banana 2](https://flux3.tools/nano-banana-2)
- [Nano Banana 2 Lite](https://flux3.tools/nano-banana-2-lite)
- [Nano Banana Pro](https://flux3.tools/nano-banana-pro)
- [Seedream 5.0 Lite](https://flux3.tools/seedream-5-0-lite)
- [Seedream 5.0 Pro](https://flux3.tools/seedream-5-0-pro)
- [Seedream 4.5](https://flux3.tools/seedream-4-5)

### Creative
- [Everygen AI Video Generator](https://flux3.tools/everygen-ai-video-generator)
- [LoreMotion AI](https://flux3.tools/loremotion-ai)
- [Narrative AI Video Editor](https://flux3.tools/narrative-ai-video-editor)
- [Prompt Seen](https://flux3.tools/prompt-seen)
- [Raindance AI](https://flux3.tools/raindance-ai)
- [Genjutsu AI](https://flux3.tools/genjutsu-ai)
- [Hotel Lobby AI](https://flux3.tools/hotel-lobby-ai)
- [Gamma AI Alternative](https://flux3.tools/gamma-ai-alternative)
- [AI Baby Generator](https://flux3.tools/ai-baby-generator)
- [Capafy AI Alternative](https://flux3.tools/capafy-ai-alternative)
- [Arena AI Alternative](https://flux3.tools/arena-ai-alternative)
- [Humanize AI](https://flux3.tools/humanize-ai)
- [AI Twerk Video Generator](https://flux3.tools/ai-twerk-video-generator)
- [Bigfoot Video Generator](https://flux3.tools/bigfoot-video-generator)
- [Viblo AI Alternative](https://flux3.tools/viblo-ai-alternative)
- [Flow AI Alternative](https://flux3.tools/flow-ai-alternative)
- [Google Gemini AI Alternative](https://flux3.tools/google-gemini-ai-alternative)
- [Pruna AI Generator](https://flux3.tools/pruna-ai-generator)
- [Everygen AI Generator](https://flux3.tools/everygen-ai-generator)
- [AI Anime Generator](https://flux3.tools/ai-anime-generator)
- [AI Logo Generator](https://flux3.tools/ai-logo-generator)
- [AI Sticker Generator](https://flux3.tools/ai-sticker-generator)
- [AI Figure Generator](https://flux3.tools/ai-figure-generator)
- [AI Fashion Generator](https://flux3.tools/ai-fashion-generator)
- [AI Interior Design](https://flux3.tools/ai-interior-design-generator)
- [AI Banner Generator](https://flux3.tools/ai-banner-generator)
- [AI Ad Creative Generator](https://flux3.tools/ai-ad-creative-generator)
- [AI Tattoo Generator](https://flux3.tools/ai-tattoo-generator)
- [AI Meme Generator](https://flux3.tools/ai-meme-generator)
- [AI QR Code Generator](https://flux3.tools/ai-qr-code-generator)
- [AI Wallpaper Generator](https://flux3.tools/ai-wallpaper-generator)
- [AI YouTube Thumbnail](https://flux3.tools/ai-youtube-thumbnail-generator)
- [AI Social Media Posts](https://flux3.tools/ai-social-media-post-generator)
- [AI Sketch to Image](https://flux3.tools/ai-sketch-to-image)
- [AI Book Cover Generator](https://flux3.tools/ai-book-cover-generator)
- [AI Icon Generator](https://flux3.tools/ai-icon-generator)
- [AI Pixel Art Generator](https://flux3.tools/ai-pixel-art-generator)

## Guides, pricing and policies
- [Prompts](https://flux3.tools/minimax-h3-max-prompts)
- [Tutorials](https://flux3.tools/blog)
- [Pricing](https://flux3.tools/pricing)
- [Privacy](https://flux3.tools/privacy-policy)
- [Terms](https://flux3.tools/terms-of-service)
- [Refund policy](https://flux3.tools/refund-policy)
- Contact: hi@flux3.tools

## AI documents
- [Short overview and index](https://flux3.tools/llms.txt)
- [Combined full reference](https://flux3.tools/llms-full.txt)
- [Plans, credits and configured default quotes](https://flux3.tools/pricing.md)
- [Connected model capabilities and settings](https://flux3.tools/models.md)

These public references follow the application configuration in the current deployment. They do not grant API access. Check the workspace quote and checkout for the selected settings, discounts and applicable tax.

---

# Flux 3 Tools pricing and credits

Canonical page: https://flux3.tools/pricing
Currency: USD. Base catalog prices are generated from the same configuration as the purchase UI; checkout determines applicable promotions and tax. Annual price below is the total annual charge, not the monthly charge. Annual credits are the configured annual grant, not an additional monthly grant.

## Subscriptions
| Plan | Monthly charge | Monthly grant | Annual charge | Annual grant |
| --- | --- | --- | --- | --- |
| 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 |

## One-time credit packs
| Pack | One-time charge | Credit grant |
| --- | --- | --- |
| Starter | $39.90 | 800 |
| Value | $79.90 | 2000 |
| Pro | $199.90 | 7500 |
| Bulk | $999.90 | 50000 |
| Mega | $2599.00 | 160000 |

## Credit rules
- Monthly subscription credits: 30-day validity from grant.
- Annual subscription credits: 365-day validity from grant.
- Credit-pack credits: 365-day validity from grant.
- Credit purchase cost and generation credit consumption are separate. The same model/settings use the same generation credits on monthly, annual and pack purchases.
- Review the quote before Create. Credits are reserved for generation and settled on confirmed completion; confirmed failed runs release/refund their reserved credits. A pending or ambiguous task is not a confirmed failure.
- Monetary refunds follow https://flux3.tools/refund-policy; do not confuse releasing generation credits with refunding a payment.
- Explicit purchase remains available; insufficient generation credits and restricted downloads can open pricing.

## Flux 3 output quotes
Video text generation and single-first-frame animation share this schedule. Adding an end frame uses the same rate, restricted to 720p / 1080p. Audio on/off has no listed surcharge. Durations are 5–20 whole seconds; the following samples use the actual shared quote engine.
| Video resolution | 5 seconds | 10 seconds | 20 seconds |
| --- | --- | --- | --- |
| 720p | 85 | 170 | 340 |
| 1080p | 145 | 290 | 580 |
| 1440p | 160 | 320 | 640 |
| 2160p | 235 | 470 | 940 |
- Image generation or reference editing: 5 credits for one 1K output. Editing supports up to ten references. Higher image tiers are not offered while partner pricing is verified.

### Keyframes and extension
These workflows use their own model choice in the Flux 3 Video workspace. Quotes below charge generated output seconds, not source clip duration. Audio on/off has no listed surcharge. Automatic duration and unpriced resolutions are unavailable.
| Workflow | Resolution | 5 seconds | 10 seconds | 20 seconds |
| --- | --- | --- | --- | --- |
| Flux 3 Keyframes | 720p | 85 | 170 | 340 |
| Flux 3 Keyframes | 1080p | 145 | 290 | 580 |
| Flux 3 Extend | 720p | 205 | 410 | 820 |
| Flux 3 Extend | 1080p | 265 | 530 | 1060 |

## Opus motion graphics
- [Opus 5.5 Video Generator](https://flux3.tools/opus-5-5-video-generator) uses a separate motion-graphics workflow.
- Each operation uses a quoted credit reservation; the configured whole-operation ceiling is 92 credits. The actual quote depends on the prompt, references and revision context. Final settlement follows the confirmed operation cost; unused reserved credits are released. This is not a fixed credits-per-second video-generation rate.

## Video models: configured default quotes
| Model | Default quote and configuration |
| --- | --- |
| Flux 3 Video | From 85 credits · default 5s · 720p |
| Flux 3 Keyframes | From 85 credits · default 5s · 720p |
| Flux 3 Extend | From 205 credits · default 5s · 720p |
| MiniMax H3 Max Turbo | From 7 credits · default 5s · 480P |
| MiniMax H3 | From 130 credits · default 5s · 2K |
| H3 Max | From 50 credits · default 5s · 768P |
| Seedance 2.5 | From 84 credits · default 4s · 480p |
| Seedance 2.0 Fast | From 44 credits · default 4s · 480p |
| Seedance 2.0 Pro | From 55 credits · default 4s · 480p |
| Seedance 2.0 Mini | From 29 credits · default 4s · 480p |
| Seedance 1.5 Pro | From 5 credits · default 4s · 480p |
| Wan 2.7 | From 50 credits · default 5s · 720p |
| Wan 2.6 | From 50 credits · default 5s · 720p |
| Grok Imagine | From 42 credits · default 6s · 720p |
| Kling 3.0 | From 26 credits · default 3s · 720p |
| PixVerse Extend | From 20 credits · default 5s · 720p |
| ByteDance Video Upscaler | From 4 credits · default 5s input · 1080p |
| Bria Video Background Removal | From 70 credits · default 5s input · source |
| PixVerse Person Swap | From 20 credits · default 5s input · 720p |
| Sync Lip Sync 2 | From 25 credits · default 5s input · source |
| Sync Talking Photo | From 67 credits · default 5s input · source |
| Hailuo 02 Pro | From 48 credits · default 6s · 1080p |
| Hailuo 02 Standard | From 27 credits · default 6s · 768p |
| Hailuo 2.3 Pro | From 49 credits · default 6s · 1080p |
| Hailuo 2.3 Standard | From 28 credits · default 6s · 768p |
| Seedance 1.0 Pro | From 61 credits · default 5s · 1080p |
| Wan 2.5 | From 75 credits · default 5s · 1080p |
| Kling 2.6 Pro | From 70 credits · default 5s · 1080p |
| Veo 3.1 | From 320 credits · default 8s · 720p |
| HappyHorse 1.0 | From 140 credits · default 5s · 1080p |
| HappyHorse 1.1 | From 90 credits · default 5s · 1080p |
| Grok Imagine 1.5 | From 84 credits · default 6s · 720p |
| H3 Max Styles | From 40 credits · default 5s · 768P |
| H3 Max Camera Control | From 40 credits · default 5s · 768P |
| H3 Max Lip Sync | From 40 credits · default 5s input · 768P |
| Gemini Omni | From 100 credits · default 8s · 720p |
| H3 LoRA | From 38 credits · default 5s · 768P |

## Image models: configured quote summaries
| Model | Credits and configuration |
| --- | --- |
| Flux 3 Image | 1K 5 credits/image |
| Seedream 5.0 Pro | Generate: 1K 7 · 2K 14 credits/image; extra edit references quoted in the workspace. Layer reserve: Auto/1K/1.5K 72 · 2K 144 credits; settles by actual layers with excess refunded |
| GPT Image 2.5 Flare | 1K square: low 4 · medium 4 · high 6 · xhigh 10 · max 22; High square: 1K 6 · 2K 11 · 4K 18 credits/image. Other ratios and custom sizes are quoted in the workspace; Auto uses the supported ceiling. |
| GPT Image 2.5 Sunburst | 1K square: low 4 · medium 4 · high 6 · xhigh 10 · max 22; High square: 1K 6 · 2K 11 · 4K 18 credits/image. Other ratios and custom sizes are quoted in the workspace; Auto uses the supported ceiling. |
| GPT Image 2 | Square/auto: 1K 19 · 2K 25 · 4K 38; non-square: 1K 22 · 2K 27 · 4K 41 credits/image |
| Nano Banana 2 | 1K 8 · 2K 12 · 4K 16 credits/image |
| Nano Banana Pro | 1K 15 · 2K 15 · 4K 30 credits/image |
| Nano Banana | default 4 credits/image |
| Seedream 5 Lite | 2K 4 · 3K 4 credits/image |
| Seedream 4.5 | 2K 4 · 4K 4 credits/image |
| Seedream V4 | 1K 4 · 2K 4 · 4K 4 credits/image |
| Bria RMBG 2.0 | original 4 credits/image |
| Illusion Diffusion | 1K 4 credits/image |
| Z-Image | default 4 credits/image |
| Nano Banana 2 Lite | 1K 5 credits/image |
| GPT Image 1.5 | 1K 14 credits/image |

These summaries reuse the pricing-page quote logic. Video processing rows may quote a sample input duration. Duration, resolution, aspect ratio, audio, references, quality and output count can change the final quote; compare identical settings. Layer decomposition can reserve an upper bound and refund unused credits on settlement. Free browser image tools do not consume AI generation credits.

---

# Flux 3 Tools connected models

Canonical tools: https://flux3.tools/ai-video-generator and https://flux3.tools/ai-image-generator
Generated from the working studio's model configuration. Only configured modes and inputs are listed; capability availability and output quality are not guarantees. Tool/alternative pages in llms.txt are discovery entries, not additional connected models. See https://flux3.tools/pricing.md for shared quote summaries and use the workspace for the final quote.

## Separate motion-graphics workflow
### Opus 5.5 · Motion Graphics
- Model ID: claude-opus-5-5-motion
- Tool: https://flux3.tools/opus-5-5-video-generator
- Prompt maximum: 6000 characters
- Durations: 10, 15, 20, 30 seconds
- Resolutions: 720p, 1080p
- Aspect ratios: 16:9, 9:16, 1:1
- Styles: Sketch, Motion
- Image references: up to 4
- Defaults: 20s, 720p, 16:9; audio off
- Quoted operation reservation, ceiling 92 credits; see pricing.md. Builds motion graphics with a separate scene/render workflow rather than the conventional video-provider pipeline.

## Video generation and processing
### Flux 3 Video
- Model ID: flux-3-video
- Provider label: Black Forest Labs
- Operation: generation
- Modes: text, image
- 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
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 10000 characters.
- Audio: optional audio control
- Optional end frame: true (two ordered images; 720p / 1080p only); seed control: false
- Defaults: text, 5s, 720p, 16:9, audio on.

### Flux 3 Keyframes
- Model ID: flux-3-keyframes
- Provider label: Black Forest Labs
- Operation: generation
- Modes: reference
- 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
- Reference upload limits: 10 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 10000 characters.
- Audio: optional audio control
- Optional end frame: false; seed control: false
- Defaults: reference, 5s, 720p, 16:9, audio on.
- Keyframe indices: unique integers from 0 through duration × 24 at 24 fps. Leave positions blank to spread inputs evenly. JPEG/PNG/WebP only.

### Flux 3 Extend
- Model ID: flux-3-extend
- Provider label: Black Forest Labs
- Operation: extend
- Modes: reference
- 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
- Reference upload limits: 0 images, 1 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 10000 characters.
- Audio: optional audio control
- Optional end frame: false; seed control: false
- Defaults: reference, 5s, 720p, 16:9, audio on.
- Source video: exactly one MP4 smaller than 50 MB and shorter than 15 seconds. Quote follows generated seconds; automatic duration is not offered.

### MiniMax H3 Max Turbo
- Model ID: minimax-h3-max-turbo
- Provider label: MiniMax
- Operation: generation
- Modes: text, image
- 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: 
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 50000 characters.
- Audio: native audio
- Optional end frame: true; seed control: true
- Defaults: text, 5s, 480P, 16:9, audio on.

### MiniMax H3
- Model ID: minimax-h3
- Provider label: MiniMax
- Operation: generation
- Modes: reference, text, image
- 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: 
- Reference upload limits: 9 images, 3 videos, 3 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 7000 characters.
- Audio: no optional audio control advertised
- Optional end frame: true; seed control: false
- Defaults: reference, 5s, 2K, adaptive, audio off.

### H3 Max
- Model ID: minimax-h3-max
- Provider label: MiniMax
- Operation: generation
- Modes: text, image
- 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: 
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 20000 characters.
- Audio: native audio
- Optional end frame: true; seed control: true
- Defaults: text, 5s, 768P, 16:9, audio on.

### Seedance 2.5
- Model ID: seedance-2.5
- Provider label: Seedance
- Operation: generation
- Modes: reference, text, image
- 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: 
- Reference upload limits: 30 images, 10 videos, 10 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 20000 characters.
- Audio: optional audio control
- Optional end frame: true; seed control: true
- Defaults: reference, 4s, 480p, adaptive, audio on.

### Seedance 2.0 Fast
- Model ID: seedance-2.0-fast
- Provider label: Seedance
- Operation: generation
- Modes: reference, text, image
- 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
- Reference upload limits: 9 images, 3 videos, 3 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 20000 characters.
- Audio: optional audio control
- Optional end frame: true; seed control: false
- Defaults: reference, 4s, 480p, adaptive, audio on.

### Seedance 2.0 Pro
- Model ID: seedance-2.0-pro
- Provider label: Seedance
- Operation: generation
- Modes: reference, text, image
- 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
- Reference upload limits: 9 images, 3 videos, 3 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 20000 characters.
- Audio: optional audio control
- Optional end frame: true; seed control: false
- Defaults: reference, 4s, 480p, adaptive, audio on.

### Seedance 2.0 Mini
- Model ID: seedance-2.0-mini
- Provider label: Seedance
- Operation: generation
- Modes: reference, text, image
- 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
- Reference upload limits: 9 images, 3 videos, 3 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 20000 characters.
- Audio: optional audio control
- Optional end frame: true; seed control: false
- Defaults: reference, 4s, 480p, adaptive, audio on.

### Seedance 1.5 Pro
- Model ID: seedance-1.5-pro
- Provider label: Seedance
- Operation: generation
- Modes: text, image
- 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
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 20000 characters.
- Audio: optional audio control
- Optional end frame: true; seed control: true
- Defaults: text, 4s, 480p, 16:9, audio off.

### Wan 2.7
- Model ID: wan-2.7
- Provider label: Wan
- Operation: generation
- Modes: text, image
- 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: 
- Reference upload limits: 2 images, 1 videos, 1 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 5000 characters.
- Audio: no optional audio control advertised
- Optional end frame: true; seed control: false
- Defaults: text, 5s, 720p, 16:9, audio off.

### Wan 2.6
- Model ID: wan-2.6
- Provider label: Wan
- Operation: generation
- Modes: text, image
- Resolutions: 720P, 1080P
- Duration options (seconds): 5, 10, 15
- Aspect ratios by mode: text: ; image: 
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 1500 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: text, 5s, 720p, 16:9, audio off.

### Grok Imagine
- Model ID: grok-imagine
- Provider label: Grok
- Operation: generation
- Modes: text, image
- Resolutions: 720P
- Duration options (seconds): 6, 10
- Aspect ratios by mode: text: 16:9, 9:16, 1:1, 3:2, 2:3; image: 
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 5000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: text, 6s, 720p, 16:9, audio off.

### Kling 3.0
- Model ID: kling-3.0
- Provider label: Kling
- Operation: generation
- Modes: text, image
- Resolutions: 720P
- Duration options (seconds): 3–15, step 1
- Aspect ratios by mode: text: 16:9, 9:16, 1:1; image: 
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2500 characters.
- Audio: optional audio control
- Optional end frame: true; seed control: false
- Defaults: text, 3s, 720p, 16:9, audio off.

### PixVerse Extend
- Model ID: pixverse-extend
- Provider label: PixVerse
- Operation: extend
- Modes: reference
- Resolutions: 360P, 540P, 720P, 1080P
- Duration options (seconds): 5
- Aspect ratios by mode: reference: 
- Reference upload limits: 0 images, 1 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: reference, 5s, 720p, adaptive, audio off.

### ByteDance Video Upscaler
- Model ID: bytedance-video-upscaler
- Provider label: ByteDance
- Operation: upscale
- Modes: reference
- Resolutions: 1080P, 2K, 4K
- Duration options (seconds): 5
- Aspect ratios by mode: reference: 
- Reference upload limits: 0 images, 1 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: optional; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: reference, 5s, 1080p, adaptive, audio off.

### Bria Video Background Removal
- Model ID: bria-video-background
- Provider label: Bria
- Operation: remove-background
- Modes: reference
- Resolutions: Source
- Duration options (seconds): 5
- Aspect ratios by mode: reference: 
- Reference upload limits: 0 images, 1 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: optional; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: reference, 5s, source, adaptive, audio off.

### PixVerse Person Swap
- Model ID: pixverse-swap
- Provider label: PixVerse
- Operation: swap
- Modes: reference
- Resolutions: 360P, 540P, 720P
- Duration options (seconds): 5
- Aspect ratios by mode: reference: 
- Reference upload limits: 1 images, 1 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: optional; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: reference, 5s, 720p, adaptive, audio off.

### Sync Lip Sync 2
- Model ID: sync-lipsync-2
- Provider label: Sync
- Operation: lipsync
- Modes: reference
- Resolutions: Source
- Duration options (seconds): 5
- Aspect ratios by mode: reference: 
- Reference upload limits: 0 images, 1 videos, 1 audio files. Mode-specific requirements still apply.
- Prompt: optional; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: reference, 5s, source, adaptive, audio off.

### Sync Talking Photo
- Model ID: sync-talking-photo
- Provider label: Sync
- Operation: talking-photo
- Modes: reference
- Resolutions: Source
- Duration options (seconds): 5
- Aspect ratios by mode: reference: 
- Reference upload limits: 1 images, 0 videos, 1 audio files. Mode-specific requirements still apply.
- Prompt: optional; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: reference, 5s, source, adaptive, audio off.

### Hailuo 02 Pro
- Model ID: hailuo-02-pro
- Provider label: MiniMax
- Operation: generation
- Modes: text, image
- Resolutions: 1080p
- Duration options (seconds): 6
- Aspect ratios by mode: text: ; image: 
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: true; seed control: false
- Defaults: text, 6s, 1080p, 16:9, audio off.

### Hailuo 02 Standard
- Model ID: hailuo-02-standard
- Provider label: MiniMax
- Operation: generation
- Modes: text, image
- Resolutions: 768p
- Duration options (seconds): 6, 10
- Aspect ratios by mode: text: ; image: 
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: true; seed control: false
- Defaults: text, 6s, 768p, 16:9, audio off.

### Hailuo 2.3 Pro
- Model ID: hailuo-2.3-pro
- Provider label: MiniMax
- Operation: generation
- Modes: text, image
- Resolutions: 1080p
- Duration options (seconds): 6
- Aspect ratios by mode: text: ; image: 
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: text, 6s, 1080p, 16:9, audio off.

### Hailuo 2.3 Standard
- Model ID: hailuo-2.3-standard
- Provider label: MiniMax
- Operation: generation
- Modes: text, image
- Resolutions: 768p
- Duration options (seconds): 6, 10
- Aspect ratios by mode: text: ; image: 
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: false
- Defaults: text, 6s, 768p, 16:9, audio off.

### Seedance 1.0 Pro
- Model ID: seedance-1.0-pro
- Provider label: Seedance
- Operation: generation
- Modes: text, image
- 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
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2000 characters.
- Audio: no optional audio control advertised
- Optional end frame: true; seed control: true
- Defaults: text, 5s, 1080p, 16:9, audio off.

### Wan 2.5
- Model ID: wan-2.5
- Provider label: Wan
- Operation: generation
- Modes: text, image
- Resolutions: 480p, 720p, 1080p
- Duration options (seconds): 5, 10
- Aspect ratios by mode: text: 16:9, 9:16, 1:1; image: 
- Reference upload limits: 1 images, 0 videos, 1 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 1500 characters.
- Audio: native audio
- Optional end frame: false; seed control: true
- Defaults: text, 5s, 1080p, 16:9, audio on.

### Kling 2.6 Pro
- Model ID: kling-2.6-pro
- Provider label: Kling
- Operation: generation
- Modes: text, image
- Resolutions: 1080p
- Duration options (seconds): 5, 10
- Aspect ratios by mode: text: 16:9, 9:16, 1:1; image: 
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2500 characters.
- Audio: optional audio control
- Optional end frame: true; seed control: false
- Defaults: text, 5s, 1080p, 16:9, audio on.

### Veo 3.1
- Model ID: veo-3.1
- Provider label: Google
- Operation: generation
- Modes: text, image
- 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
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 20000 characters.
- Audio: optional audio control
- Optional end frame: false; seed control: true
- Defaults: text, 8s, 720p, 16:9, audio on.

### HappyHorse 1.0
- Model ID: happyhorse-1.0
- Provider label: Alibaba
- Operation: generation
- Modes: text, image
- 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: 
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2500 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: true
- Defaults: text, 5s, 1080p, 16:9, audio off.

### HappyHorse 1.1
- Model ID: happyhorse-1.1
- Provider label: Alibaba
- Operation: generation
- Modes: text, image
- 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: 
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 2500 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: true
- Defaults: text, 5s, 1080p, 16:9, audio off.

### Grok Imagine 1.5
- Model ID: grok-imagine-1.5
- Provider label: Grok
- Operation: generation
- Modes: text, image
- 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: 
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 4096 characters.
- Audio: native audio
- Optional end frame: false; seed control: false
- Defaults: text, 6s, 720p, 16:9, audio on.

### H3 Max Styles
- Model ID: h3-max-styles
- Provider label: MiniMax
- Operation: generation
- Modes: text, image
- 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: 
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 49868 characters.
- Audio: native audio
- Optional end frame: false; seed control: true
- Defaults: text, 5s, 768P, 16:9, audio on.

### H3 Max Camera Control
- Model ID: h3-max-camera-control
- Provider label: MiniMax
- Operation: generation
- Modes: image
- Resolutions: 480P, 768P, 1080P
- Duration options (seconds): 3–15, step 1
- Aspect ratios by mode: image: 
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: optional; maximum 50000 characters.
- Audio: no optional audio control advertised
- Optional end frame: false; seed control: true
- Defaults: image, 5s, 768P, 16:9, audio off.

### H3 Max Lip Sync
- Model ID: h3-max-lip-sync
- Provider label: MiniMax
- Operation: h3-lipsync
- Modes: reference
- Resolutions: 480P, 768P, 1080P, 2K
- Duration options (seconds): 5
- Aspect ratios by mode: reference: 
- Reference upload limits: 1 images, 0 videos, 1 audio files. Mode-specific requirements still apply.
- Prompt: optional; maximum 2000 characters.
- Audio: native audio
- Optional end frame: false; seed control: true
- Defaults: reference, 5s, 768P, adaptive, audio on.

### Gemini Omni
- Model ID: gemini-omni
- Provider label: Google
- Operation: generation
- Modes: text, image
- Resolutions: 720p
- Duration options (seconds): 3–10, step 1
- Aspect ratios by mode: text: 16:9, 9:16; image: 16:9, 9:16
- Reference upload limits: 1 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 20000 characters.
- Audio: native audio
- Optional end frame: false; seed control: false
- Defaults: text, 8s, 720p, 16:9, audio on.

### H3 LoRA
- Model ID: h3-lora
- Provider label: MiniMax
- Operation: generation
- Modes: text, image
- 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: 
- Reference upload limits: 2 images, 0 videos, 0 audio files. Mode-specific requirements still apply.
- Prompt: required; maximum 50000 characters.
- Audio: native audio
- Optional end frame: true; seed control: true
- Defaults: text, 5s, 768P, 16:9, audio on.



## Image generation and editing
### Flux 3 Image
- Model ID: flux-3-image
- Provider label: Black Forest Labs
- Modes: text, image
- Resolutions: 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 image limit: 10; accepted types: image/jpeg, image/png, image/webp
- Prompt maximum: 10000 characters
- Multiple outputs: false; maximum: 1
- Default resolution: 1K

### Seedream 5.0 Pro
- Model ID: seedream-5-pro
- Provider label: Seedream
- Modes: layer-decomposition, text, image
- Resolutions: 1K, 2K
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
- Reference image limit: 10; accepted types: see upload control
- Prompt maximum: 5000 characters
- Multiple outputs: true; maximum: 6
- Default resolution: 2K
- Layer decomposition resolutions: auto, 1K, 1.5K, 2K

### GPT Image 2.5 Flare
- Model ID: gpt-image-2.5-flare
- Provider label: OpenAI
- Modes: text, image
- Resolutions: 1K, 2K, 4K
- 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 image limit: 16; accepted types: see upload control
- Prompt maximum: 32000 characters
- Multiple outputs: true; maximum: 10
- Default resolution: 1K

### GPT Image 2.5 Sunburst
- Model ID: gpt-image-2.5-sunburst
- Provider label: OpenAI
- Modes: text, image
- Resolutions: 1K, 2K, 4K
- 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 image limit: 16; accepted types: see upload control
- Prompt maximum: 32000 characters
- Multiple outputs: true; maximum: 10
- Default resolution: 1K

### GPT Image 2
- Model ID: gpt-image-2
- Provider label: OpenAI
- Modes: text, image
- Resolutions: 1K, 2K, 4K
- 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 image limit: 16; accepted types: see upload control
- Prompt maximum: 20000 characters
- Multiple outputs: true; maximum: see workspace
- Default resolution: 1K

### Nano Banana 2
- Model ID: nano-banana-2
- Provider label: Nano Banana
- Modes: text, image
- Resolutions: 1K, 2K, 4K
- Aspect ratios: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
- Reference image limit: 14; accepted types: see upload control
- Prompt maximum: 20000 characters
- Multiple outputs: true; maximum: see workspace
- Default resolution: model default

### Nano Banana Pro
- Model ID: nano-banana-pro
- Provider label: Nano Banana
- Modes: text, image
- Resolutions: 1K, 2K, 4K
- Aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
- Reference image limit: 14; accepted types: see upload control
- Prompt maximum: 20000 characters
- Multiple outputs: true; maximum: see workspace
- Default resolution: model default

### Nano Banana
- Model ID: nano-banana
- Provider label: Nano Banana
- Modes: text, image
- Resolutions: model default
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9
- Reference image limit: 10; accepted types: see upload control
- Prompt maximum: 20000 characters
- Multiple outputs: true; maximum: see workspace
- Default resolution: model default

### Seedream 5 Lite
- Model ID: seedream-5-lite
- Provider label: Seedream
- Modes: text, image
- Resolutions: 2K, 3K
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9
- Reference image limit: 10; accepted types: see upload control
- Prompt maximum: 5000 characters
- Multiple outputs: true; maximum: see workspace
- Default resolution: model default

### Seedream 4.5
- Model ID: seedream-4-5
- Provider label: Seedream
- Modes: text, image
- Resolutions: 2K, 4K
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9
- Reference image limit: 10; accepted types: see upload control
- Prompt maximum: 3000 characters
- Multiple outputs: true; maximum: see workspace
- Default resolution: model default

### Seedream V4
- Model ID: seedream-v4
- Provider label: Seedream
- Modes: text, image
- Resolutions: 1K, 2K, 4K
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9
- Reference image limit: 10; accepted types: see upload control
- Prompt maximum: 5000 characters
- Multiple outputs: true; maximum: see workspace
- Default resolution: model default

### Bria RMBG 2.0
- Model ID: bria-background-remove
- Provider label: Bria
- Modes: image
- Resolutions: original
- Aspect ratios: auto
- Reference image limit: 1; accepted types: image/jpeg, image/png, image/webp
- Prompt maximum: 0 characters
- Multiple outputs: false; maximum: see workspace
- Default resolution: original

### Illusion Diffusion
- Model ID: illusion-diffusion
- Provider label: Illusion Diffusion
- Modes: image
- Resolutions: 1K
- Aspect ratios: 1:1
- Reference image limit: 1; accepted types: image/jpeg, image/png, image/webp
- Prompt maximum: 2000 characters
- Multiple outputs: false; maximum: see workspace
- Default resolution: 1K

### Z-Image
- Model ID: z-image
- Provider label: Z-Image
- Modes: text
- Resolutions: model default
- Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16
- Reference image limit: 0; accepted types: see upload control
- Prompt maximum: 1000 characters
- Multiple outputs: false; maximum: see workspace
- Default resolution: model default

### Nano Banana 2 Lite
- Model ID: nano-banana-2-lite
- Provider label: Nano Banana
- Modes: text
- Resolutions: 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 image limit: 0; accepted types: see upload control
- Prompt maximum: 50000 characters
- Multiple outputs: true; maximum: 4
- Default resolution: 1K

### GPT Image 1.5
- Model ID: gpt-image-1.5
- Provider label: OpenAI
- Modes: text, image
- Resolutions: 1K
- Aspect ratios: 1:1, 3:2, 2:3
- Reference image limit: 10; accepted types: see upload control
- Prompt maximum: 32000 characters
- Multiple outputs: true; maximum: 4
- Default resolution: 1K


Generation requires login and sufficient credits. Outputs and inputs must satisfy the selected mode's validation. Review complete generated media before use. Provider endpoints and credentials are not part of this public reference.