# Muse Spark Open

> Independent creative and office studio at https://musesparkopen.tools. English canonical documentation; the website also supports Simplified Chinese. Model/vendor names do not imply official affiliation.

## Start here

Open the homepage for AI images/video, or a tool workspace: FilmCraft video editing, PhotoCraft layered image editing, PdfCraft PDFs, WordCraft documents, GridCraft spreadsheets and DeckCraft slides. ArtCraft also provides image/video editing, music, 3D objects, worlds and character workflows. Guests can edit/import. Verified Google login is required to save/export; login and One Tap preserve live editors. Browser editing/saving uses zero credits and saves private results as AI Tasks. Paid AI actions require sufficient credits; editing alone does not submit generation.

Choose a supported mode and input, review settings and the displayed quote, then explicitly generate. Final server validation and quote govern each request; model availability can depend on provider service status. Tool/SEO page titles are not additional model integrations. See models.md for the configured workspace catalog.

## Muse Spark Open research context

The homepage includes an attributed Meta release overview. Muse Spark Open inference is not integrated in this service. The supported generation catalog below describes the actual workspaces.

## Public references

- [llms.txt](https://musesparkopen.tools/llms.txt)
- [llms-full.txt](https://musesparkopen.tools/llms-full.txt)
- [pricing.md](https://musesparkopen.tools/pricing.md)
- [models.md](https://musesparkopen.tools/models.md)
- [Pricing and checkout](https://musesparkopen.tools/pricing)
- [Tutorials](https://musesparkopen.tools/blog)
- [Prompt examples](https://musesparkopen.tools/minimax-h3-max-prompts)
- [Privacy](https://musesparkopen.tools/privacy-policy)
- [Terms](https://musesparkopen.tools/terms-of-service)
- [Refund policy](https://musesparkopen.tools/refund-policy)
- Contact: hi@musesparkopen.tools

## Tool directories

### ArtCraft
- [muse wonder open Home](https://musesparkopen.tools/artcraft)
- [muse wonder open Overview](https://musesparkopen.tools/)
- [muse wonder open Image](https://musesparkopen.tools/artcraft/create-image)
- [muse wonder open Video](https://musesparkopen.tools/artcraft/create-video)
- [muse wonder open Audio](https://musesparkopen.tools/artcraft/create-audio)
- [muse wonder open 3D Object](https://musesparkopen.tools/artcraft/create-object)
- [muse wonder open 3D World](https://musesparkopen.tools/artcraft/create-world)
- [muse wonder open Edit Image](https://musesparkopen.tools/artcraft/edit-image)
- [muse wonder open Edit 3D](https://musesparkopen.tools/artcraft/edit-3d)
- [muse wonder open Edit Video](https://musesparkopen.tools/artcraft/video-editor)
- [muse wonder open Background Change](https://musesparkopen.tools/artcraft/background-change)
- [muse wonder open Moodboard](https://musesparkopen.tools/artcraft/moodboard)
- [muse wonder open Frame Extractor](https://musesparkopen.tools/artcraft/frame-extractor)
- [muse wonder open Character Training](https://musesparkopen.tools/artcraft/characters)
- [muse wonder open Library](https://musesparkopen.tools/artcraft/library)
- [muse wonder open World Viewer](https://musesparkopen.tools/artcraft/world-viewer)
- [muse wonder open Unfoldered](https://musesparkopen.tools/artcraft/library/folderless)
- [muse wonder open Folders](https://musesparkopen.tools/artcraft/library/folders)

### Creative & Office Editors
- [muse wonder open filmcraft](https://musesparkopen.tools/filmcraft)
- [muse wonder open photocraft](https://musesparkopen.tools/photocraft)
- [muse wonder open pdfcraft](https://musesparkopen.tools/pdfcraft)
- [muse wonder open wordcraft](https://musesparkopen.tools/wordcraft)
- [muse wonder open gridcraft](https://musesparkopen.tools/gridcraft)
- [muse wonder open deckcraft](https://musesparkopen.tools/deckcraft)

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

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

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

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

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

## Documentation freshness

These documents are rendered on public requests from the same deployed catalog, credit products and quote functions used by this site. Code/config catalog changes take effect on deployment. Public backend settings (product name, default payment provider, welcome-credit settings) use the effective runtime configuration and its version invalidation. No public document grants access to private projects or administrative APIs.


---

# Muse Spark Open pricing and credits

Canonical: https://musesparkopen.tools/pricing.md

Default payment provider (effective runtime setting): stripe. Catalog below is the base USD catalog shared with the purchase UI; it does not predict tax, applied promotion codes or final checkout total. A configured catalog is not a promise that a disabled checkout is available.

## Subscriptions

| Product | Full charge and interval | Credit grant cadence | Validity from grant |
| --- | --- | --- | --- |
| Lite monthly | USD 29.90 / month | 600 on each paid monthly invoice | each subscription month |
| Lite annual | USD 179.00 / year, billed as a whole (USD 14.92 / month equivalent) | 7200 total, 600 monthly | each subscription month |
| Standard monthly | USD 49.90 / month | 1500 on each paid monthly invoice | each subscription month |
| Standard annual | USD 299.00 / year, billed as a whole (USD 24.92 / month equivalent) | 18000 total, 1500 monthly | each subscription month |
| Pro monthly | USD 99.90 / month | 3600 on each paid monthly invoice | each subscription month |
| Pro annual | USD 599.00 / year, billed as a whole (USD 49.92 / month equivalent) | 43200 total, 3600 monthly | each subscription month |
| Max monthly | USD 199.90 / month | 8000 on each paid monthly invoice | each subscription month |
| Max annual | USD 1199.00 / year, billed as a whole (USD 99.92 / month equivalent) | 96000 total, 8000 monthly | each subscription month |

## One-time credit packs

| Pack | Full charge | Credits on payment | Validity from grant |
| --- | --- | --- | --- |
| Starter | USD 39.90 once | 800 | 365 days |
| Value | USD 79.90 once | 2000 | 365 days |
| Pro | USD 199.90 once | 7500 | 365 days |
| Bulk | USD 999.90 once | 50000 | 365 days |
| Mega | USD 2599.00 once | 160000 | 365 days |

Credits are granted on confirmed payment and expire according to the grant, not a promise of unlimited use. Welcome credits: disabled.

## Image quote examples

| Model | Example settings | Credits per request |
| --- | --- | --- |
| Seedream 5.0 Pro (seedream-5-pro) | 2K, 1:1, high where supported, 1 output, 0 reference(s) | 14 |
| GPT Image 2.5 Flare (gpt-image-2.5-flare) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 6 |
| GPT Image 2.5 Sunburst (gpt-image-2.5-sunburst) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 6 |
| GPT Image 2 (gpt-image-2) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 19 |
| Nano Banana 2 (nano-banana-2) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 8 |
| Nano Banana Pro (nano-banana-pro) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 15 |
| Nano Banana (nano-banana) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 4 |
| Seedream 5 Lite (seedream-5-lite) | 2K, 1:1, high where supported, 1 output, 0 reference(s) | 4 |
| Seedream 4.5 (seedream-4-5) | 2K, 1:1, high where supported, 1 output, 0 reference(s) | 4 |
| Seedream V4 (seedream-v4) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 4 |
| Bria RMBG 2.0 (bria-background-remove) | original, 1:1, high where supported, 1 output, 1 reference(s) | 4 |
| Illusion Diffusion (illusion-diffusion) | 1K, 1:1, high where supported, 1 output, 1 reference(s) | 4 |
| Z-Image (z-image) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 4 |
| Nano Banana 2 Lite (nano-banana-2-lite) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 5 |
| GPT Image 1.5 (gpt-image-1.5) | 1K, 1:1, high where supported, 1 output, 0 reference(s) | 14 |

## Video generation / processing quote examples

| Model | Example settings | Credits per request |
| --- | --- | --- |
| MiniMax H3 Max Turbo (minimax-h3-max-turbo) | text, 5s output, 480P, 16:9, audio true, default version | 7 |
| MiniMax H3 (minimax-h3) | reference, 5s output, 2K, adaptive, audio false, default version | 130 |
| H3 Max (minimax-h3-max) | text, 5s output, 768P, 16:9, audio true, default version | 50 |
| Seedance 2.5 (seedance-2.5) | reference, 4s output, 480p, adaptive, audio true, default version | 84 |
| Seedance 2.0 Fast (seedance-2.0-fast) | reference, 4s output, 480p, adaptive, audio true, default version | 44 |
| Seedance 2.0 Pro (seedance-2.0-pro) | reference, 4s output, 480p, adaptive, audio true, default version | 55 |
| Seedance 2.0 Mini (seedance-2.0-mini) | reference, 4s output, 480p, adaptive, audio true, default version | 29 |
| Seedance 1.5 Pro (seedance-1.5-pro) | text, 4s output, 480p, 16:9, audio false, default version | 5 |
| Wan 2.7 (wan-2.7) | text, 5s output, 720p, 16:9, audio false, default version | 50 |
| Wan 2.6 (wan-2.6) | text, 5s output, 720p, 16:9, audio false, default version | 50 |
| Grok Imagine (grok-imagine) | text, 6s output, 720p, 16:9, audio false, default version | 42 |
| Kling 3.0 (kling-3.0) | text, 3s output, 720p, 16:9, audio false, standard | 26 |
| PixVerse Extend (pixverse-extend) | reference, 5s output, 720p, adaptive, audio false, default version; 5s input media for operation example | 20 |
| ByteDance Video Upscaler (bytedance-video-upscaler) | reference, 5s output, 1080p, adaptive, audio false, default version; 5s input media for operation example | 4 |
| Bria Video Background Removal (bria-video-background) | reference, 5s output, source, adaptive, audio false, default version; 5s input media for operation example | 70 |
| PixVerse Person Swap (pixverse-swap) | reference, 5s output, 720p, adaptive, audio false, default version; 5s input media for operation example | 20 |
| Sync Lip Sync 2 (sync-lipsync-2) | reference, 5s output, source, adaptive, audio false, default version; 5s input media for operation example | 25 |
| Sync Talking Photo (sync-talking-photo) | reference, 5s output, source, adaptive, audio false, default version; 5s input media for operation example | 67 |
| Hailuo 02 Pro (hailuo-02-pro) | text, 6s output, 1080p, 16:9, audio false, default version | 48 |
| Hailuo 02 Standard (hailuo-02-standard) | text, 6s output, 768p, 16:9, audio false, default version | 27 |
| Hailuo 2.3 Pro (hailuo-2.3-pro) | text, 6s output, 1080p, 16:9, audio false, default version | 49 |
| Hailuo 2.3 Standard (hailuo-2.3-standard) | text, 6s output, 768p, 16:9, audio false, default version | 28 |
| Seedance 1.0 Pro (seedance-1.0-pro) | text, 5s output, 1080p, 16:9, audio false, default version | 61 |
| Wan 2.5 (wan-2.5) | text, 5s output, 1080p, 16:9, audio true, default version | 75 |
| Kling 2.6 Pro (kling-2.6-pro) | text, 5s output, 1080p, 16:9, audio true, default version | 70 |
| Veo 3.1 (veo-3.1) | text, 8s output, 720p, 16:9, audio true, default version | 320 |
| HappyHorse 1.0 (happyhorse-1.0) | text, 5s output, 1080p, 16:9, audio false, default version | 140 |
| HappyHorse 1.1 (happyhorse-1.1) | text, 5s output, 1080p, 16:9, audio false, default version | 90 |
| Grok Imagine 1.5 (grok-imagine-1.5) | text, 6s output, 720p, 16:9, audio true, default version | 84 |
| H3 Max Styles (h3-max-styles) | text, 5s output, 768P, 16:9, audio true, default version | 40 |
| H3 Max Camera Control (h3-max-camera-control) | image, 5s output, 768P, 16:9, audio false, default version | 40 |
| H3 Max Lip Sync (h3-max-lip-sync) | reference, 5s output, 768P, adaptive, audio true, default version; 5s input media for operation example | 40 |
| Gemini Omni (gemini-omni) | text, 8s output, 720p, 16:9, audio true, default version | 100 |
| H3 LoRA (h3-lora) | text, 5s output, 768P, 16:9, audio true, default version | 38 |

Examples call the real quote functions with the stated configuration, not fixed output allowances or a per-second tariff. References, reference duration, resolution, ratio, audio, quality, version, output count and other supported settings can change the quote. GPT Image 2.5 quotes are output estimates; auto uses the supported ceiling. Review the workspace quote before submitting.

## Separate workflows

- Layer decomposition: reserve up to 16 outputs, 72 credits Auto/1K/1.5K or 144 credits 2K; settle by actual returned layer count and release unused reservation.
- ACE-Step · Fal: 2 credits / 60-second music operation.
- Hunyuan3D V3 · Fal normal: 38 credits / object without PBR; 53 with PBR.
- Hunyuan3D V3 · Fal low_poly: 45 credits / object without PBR; 60 with PBR.
- Hunyuan3D V3 · Fal geometry: 23 credits / object without PBR; 38 with PBR.
- Marble marble-1.0-draft: 19 credits reserved for text/ordinary image; 12 for panorama. Provider receipt settles at or below reservation; unused credit is released.
- Marble marble-1.1: 127 credits reserved for text/ordinary image; 120 for panorama. Provider receipt settles at or below reservation; unused credit is released.
- Marble marble-1.1-plus: 247 credits reserved for text/ordinary image; 240 for panorama. Provider receipt settles at or below reservation; unused credit is released.
- FLUX Pro Fill: 5 credits for a 1-megapixel masked edit; input/mask must match, maximum 4 megapixels.
- Video background replacement: 140 credits for a 5-second MP4/MOV input, fixed 720p, optional reference image; validated inputs are 3–15 seconds.
- Character training: 2000 credits / 1000-step training operation with 4–20 distinct images (15 MB combined). A ready character image costs 7 credits / 1024×1024 output.
- Humanize (google/gemini-2.5-flash): input-dependent reservation; sample “Rewrite this sentence clearly.”, natural tone reserves 3 credits; receipt-based usage settlement releases unused reservation.
- Prompt Seen vision (google/gemini-2.5-flash): 2 credits reserved / image-to-prompt operation; receipt-based settlement, capped at reservation.

Browser edits and authenticated browser saves/exports use zero credits and create private AI Tasks. AI requests reserve credits before submission; successful results capture credits and confirmed failures return reserved credits. Pending or ambiguous requests await reconciliation; do not assume an immediate refund. Partial results and layered/text/world workflows can release unused reservation according to their settlement. Credit restoration is distinct from a cash payment refund. Cash refunds follow [the refund policy](https://musesparkopen.tools/refund-policy); see [terms](https://musesparkopen.tools/terms-of-service) and [current checkout](https://musesparkopen.tools/pricing).


---

# Muse Spark Open models and workflows

Canonical: https://musesparkopen.tools/models.md

This catalog comes from the configured live workspaces, not marketing landing-page names. Availability remains subject to provider operations and validated inputs. Model names are public stable application identifiers, not provider credentials or endpoints. See [pricing and configuration-dependent examples](https://musesparkopen.tools/pricing.md). No capability beyond these settings is guaranteed. The ArtCraft compatibility picker exposes a subset of this catalog; specialist tools use their own modes.

## Image generation, editing and layers

### Seedream 5.0 Pro — seedream-5-pro
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: layer-decomposition, text, image. Prompt limit: 5000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K, 2K; default 2K. Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3.
- Maximum reference images: 10; outputs: up to 6. Input upload validation depends on mode. Maximum image bytes: 31457280.
- Output: workspace/provider format; layer resolutions: auto, 1K, 1.5K, 2K; layer types: image/jpeg, image/png, image/webp, image/bmp, image/tiff, image/gif.

### GPT Image 2.5 Flare — gpt-image-2.5-flare
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 32000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K, 2K, 4K; default 1K. 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.
- Maximum reference images: 16; outputs: up to 10. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.
- Quality: auto, low, medium, high, xhigh, max (default high); background: auto, transparent, opaque (default auto); output formats: png, jpeg, webp (default png). Custom dimensions: multiples of 16, maximum edge 3840, pixels 655360–8294400, maximum aspect ratio 3.

### GPT Image 2.5 Sunburst — gpt-image-2.5-sunburst
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 32000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K, 2K, 4K; default 1K. 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.
- Maximum reference images: 16; outputs: up to 10. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.
- Quality: auto, low, medium, high, xhigh, max (default high); background: auto, transparent, opaque (default auto); output formats: png, jpeg, webp (default png). Custom dimensions: multiples of 16, maximum edge 3840, pixels 655360–8294400, maximum aspect ratio 3.

### GPT Image 2 — gpt-image-2
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 20000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K, 2K, 4K; default 1K. 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.
- Maximum reference images: 16; outputs: up to workspace limit. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.

### Nano Banana 2 — nano-banana-2
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 20000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K, 2K, 4K; default 1K. Ratios: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9.
- Maximum reference images: 14; outputs: up to workspace limit. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.

### Nano Banana Pro — nano-banana-pro
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 20000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K, 2K, 4K; default 1K. Ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9.
- Maximum reference images: 14; outputs: up to workspace limit. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.

### Nano Banana — nano-banana
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 20000 characters; prompt required where the mode uses a prompt.
- Resolutions: original/default; default default. Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Maximum reference images: 10; outputs: up to workspace limit. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.

### Seedream 5 Lite — seedream-5-lite
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 5000 characters; prompt required where the mode uses a prompt.
- Resolutions: 2K, 3K; default 2K. Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Maximum reference images: 10; outputs: up to workspace limit. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.

### Seedream 4.5 — seedream-4-5
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 3000 characters; prompt required where the mode uses a prompt.
- Resolutions: 2K, 4K; default 2K. Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Maximum reference images: 10; outputs: up to workspace limit. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.

### Seedream V4 — seedream-v4
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 5000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K, 2K, 4K; default 1K. Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Maximum reference images: 10; outputs: up to workspace limit. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.

### Bria RMBG 2.0 — bria-background-remove
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: image. Prompt limit: 0 characters; prompt optional.
- Resolutions: original; default original. Ratios: auto.
- Maximum reference images: 1; outputs: 1. Input types: image/jpeg, image/png, image/webp. Maximum image bytes: 31457280.
- Output: png; no layer mode configured.

### Illusion Diffusion — illusion-diffusion
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: image. Prompt limit: 2000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K; default 1K. Ratios: 1:1.
- Maximum reference images: 1; outputs: 1. Input types: image/jpeg, image/png, image/webp. Maximum image bytes: 10485760.
- Output: png; no layer mode configured.

### Z-Image — z-image
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text. Prompt limit: 1000 characters; prompt required where the mode uses a prompt.
- Resolutions: original/default; default default. Ratios: 1:1, 4:3, 3:4, 16:9, 9:16.
- Maximum reference images: 0; outputs: 1. Input upload validation depends on mode. 
- Output: workspace/provider format; no layer mode configured.

### Nano Banana 2 Lite — nano-banana-2-lite
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text. Prompt limit: 50000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K; default 1K. 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.
- Maximum reference images: 0; outputs: up to 4. Input upload validation depends on mode. 
- Output: png; no layer mode configured.

### GPT Image 1.5 — gpt-image-1.5
- Workspace: https://musesparkopen.tools/ai-image-generator; modes: text, image. Prompt limit: 32000 characters; prompt required where the mode uses a prompt.
- Resolutions: 1K; default 1K. Ratios: 1:1, 3:2, 2:3.
- Maximum reference images: 10; outputs: up to 4. Input upload validation depends on mode. 
- Output: png; no layer mode configured.

## Video generation and processing

### MiniMax H3 Max Turbo — minimax-h3-max-turbo
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 50000 characters; prompt required: true.
- Resolutions: 480P, 768P, 1080P; duration seconds: 5–15, step 1.
- Defaults: mode text, 5s, 480P, 16:9, audio true. Versions: not selectable.
- text: ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: native; end frame: true; seed: true; formats: workspace/provider format.

### MiniMax H3 — minimax-h3
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: reference, text, image. Prompt limit: 7000 characters; prompt required: true.
- Resolutions: 2K; duration seconds: 5–15, step 1.
- Defaults: mode reference, 5s, 2K, adaptive, audio false. Versions: not selectable.
- reference: ratios adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, input limits {"images":9,"videos":3,"audio":3,"total":12}; text: ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: no toggle; end frame: true; seed: false; formats: workspace/provider format.

### H3 Max — minimax-h3-max
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 20000 characters; prompt required: true.
- Resolutions: 480P, 768P; duration seconds: 5–15, step 1.
- Defaults: mode text, 5s, 768P, 16:9, audio true. Versions: not selectable.
- text: ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: native; end frame: true; seed: true; formats: workspace/provider format.

### Seedance 2.5 — seedance-2.5
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: reference, text, image. Prompt limit: 20000 characters; prompt required: true.
- Resolutions: 480p, 720p; duration seconds: 4–30, step 1.
- Defaults: mode reference, 4s, 480p, adaptive, audio true. Versions: not selectable.
- reference: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":30,"videos":10,"audio":10,"total":50}; text: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: optional; end frame: true; seed: true; formats: workspace/provider format.

### Seedance 2.0 Fast — seedance-2.0-fast
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: reference, text, image. Prompt limit: 20000 characters; prompt required: true.
- Resolutions: 480p, 720p; duration seconds: 4–15, step 1.
- Defaults: mode reference, 4s, 480p, adaptive, audio true. Versions: not selectable.
- reference: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":9,"videos":3,"audio":3,"total":12}; text: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: optional; end frame: true; seed: false; formats: workspace/provider format.

### Seedance 2.0 Pro — seedance-2.0-pro
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: reference, text, image. Prompt limit: 20000 characters; prompt required: true.
- Resolutions: 480p, 720p, 1080p, 4k; duration seconds: 4–15, step 1.
- Defaults: mode reference, 4s, 480p, adaptive, audio true. Versions: not selectable.
- reference: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":9,"videos":3,"audio":3,"total":12}; text: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: optional; end frame: true; seed: false; formats: workspace/provider format.

### Seedance 2.0 Mini — seedance-2.0-mini
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: reference, text, image. Prompt limit: 20000 characters; prompt required: true.
- Resolutions: 480p, 720p; duration seconds: 4–15, step 1.
- Defaults: mode reference, 4s, 480p, adaptive, audio true. Versions: not selectable.
- reference: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":9,"videos":3,"audio":3,"total":12}; text: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios adaptive, 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: optional; end frame: true; seed: false; formats: workspace/provider format.

### Seedance 1.5 Pro — seedance-1.5-pro
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 20000 characters; prompt required: true.
- Resolutions: 480p, 720p, 1080p; duration seconds: 4, 8, 12.
- Defaults: mode text, 4s, 480p, 16:9, audio false. Versions: not selectable.
- text: ratios 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: optional; end frame: true; seed: true; formats: workspace/provider format.

### Wan 2.7 — wan-2.7
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 5000 characters; prompt required: true.
- Resolutions: 720p, 1080p; duration seconds: 2–15, step 1.
- Defaults: mode text, 5s, 720p, 16:9, audio false. Versions: not selectable.
- text: ratios 16:9, 9:16, 1:1, 4:3, 3:4, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: no toggle; end frame: true; seed: false; formats: workspace/provider format.

### Wan 2.6 — wan-2.6
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 1500 characters; prompt required: true.
- Resolutions: 720p, 1080p; duration seconds: 5, 10, 15.
- Defaults: mode text, 5s, 720p, 16:9, audio false. Versions: not selectable.
- text: ratios from input/default, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### Grok Imagine — grok-imagine
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 5000 characters; prompt required: true.
- Resolutions: 720p; duration seconds: 6, 10.
- Defaults: mode text, 6s, 720p, 16:9, audio false. Versions: not selectable.
- text: ratios 16:9, 9:16, 1:1, 3:2, 2:3, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### Kling 3.0 — kling-3.0
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 2500 characters; prompt required: true.
- Resolutions: 720p; duration seconds: 3–15, step 1.
- Defaults: mode text, 3s, 720p, 16:9, audio false. Versions: standard, pro.
- text: ratios 16:9, 9:16, 1:1, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: optional; end frame: true; seed: false; formats: workspace/provider format.

### PixVerse Extend — pixverse-extend
- Workspace: https://musesparkopen.tools/ai-video-generator; operation: extend; modes: reference. Prompt limit: 2000 characters; prompt required: true.
- Resolutions: 360p, 540p, 720p, 1080p; duration seconds: 5.
- Defaults: mode reference, 5s, 720p, adaptive, audio false. Versions: not selectable.
- reference: ratios from input/default, input limits {"images":0,"videos":1,"audio":0}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### ByteDance Video Upscaler — bytedance-video-upscaler
- Workspace: https://musesparkopen.tools/ai-video-generator; operation: upscale; modes: reference. Prompt limit: 2000 characters; prompt required: false.
- Resolutions: 1080p, 2k, 4k; duration seconds: 5.
- Defaults: mode reference, 5s, 1080p, adaptive, audio false. Versions: not selectable.
- reference: ratios from input/default, input limits {"images":0,"videos":1,"audio":0}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### Bria Video Background Removal — bria-video-background
- Workspace: https://musesparkopen.tools/ai-video-generator; operation: remove-background; modes: reference. Prompt limit: 2000 characters; prompt required: false.
- Resolutions: source; duration seconds: 5.
- Defaults: mode reference, 5s, source, adaptive, audio false. Versions: not selectable.
- reference: ratios from input/default, input limits {"images":0,"videos":1,"audio":0}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### PixVerse Person Swap — pixverse-swap
- Workspace: https://musesparkopen.tools/ai-video-generator; operation: swap; modes: reference. Prompt limit: 2000 characters; prompt required: false.
- Resolutions: 360p, 540p, 720p; duration seconds: 5.
- Defaults: mode reference, 5s, 720p, adaptive, audio false. Versions: not selectable.
- reference: ratios from input/default, input limits {"images":1,"videos":1,"audio":0}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### Sync Lip Sync 2 — sync-lipsync-2
- Workspace: https://musesparkopen.tools/ai-video-generator; operation: lipsync; modes: reference. Prompt limit: 2000 characters; prompt required: false.
- Resolutions: source; duration seconds: 5.
- Defaults: mode reference, 5s, source, adaptive, audio false. Versions: not selectable.
- reference: ratios from input/default, input limits {"images":0,"videos":1,"audio":1}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### Sync Talking Photo — sync-talking-photo
- Workspace: https://musesparkopen.tools/ai-video-generator; operation: talking-photo; modes: reference. Prompt limit: 2000 characters; prompt required: false.
- Resolutions: source; duration seconds: 5.
- Defaults: mode reference, 5s, source, adaptive, audio false. Versions: not selectable.
- reference: ratios from input/default, input limits {"images":1,"videos":0,"audio":1}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### Hailuo 02 Pro — hailuo-02-pro
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 2000 characters; prompt required: true.
- Resolutions: 1080p; duration seconds: 6.
- Defaults: mode text, 6s, 1080p, 16:9, audio false. Versions: not selectable.
- text: ratios from input/default, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: no toggle; end frame: true; seed: false; formats: workspace/provider format.

### Hailuo 02 Standard — hailuo-02-standard
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 2000 characters; prompt required: true.
- Resolutions: 768p; duration seconds: 6, 10.
- Defaults: mode text, 6s, 768p, 16:9, audio false. Versions: not selectable.
- text: ratios from input/default, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: no toggle; end frame: true; seed: false; formats: workspace/provider format.

### Hailuo 2.3 Pro — hailuo-2.3-pro
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 2000 characters; prompt required: true.
- Resolutions: 1080p; duration seconds: 6.
- Defaults: mode text, 6s, 1080p, 16:9, audio false. Versions: not selectable.
- text: ratios from input/default, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### Hailuo 2.3 Standard — hailuo-2.3-standard
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 2000 characters; prompt required: true.
- Resolutions: 768p; duration seconds: 6, 10.
- Defaults: mode text, 6s, 768p, 16:9, audio false. Versions: not selectable.
- text: ratios from input/default, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: no toggle; end frame: false; seed: false; formats: workspace/provider format.

### Seedance 1.0 Pro — seedance-1.0-pro
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 2000 characters; prompt required: true.
- Resolutions: 480p, 720p, 1080p; duration seconds: 2–12, step 1.
- Defaults: mode text, 5s, 1080p, 16:9, audio false. Versions: not selectable.
- text: ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios auto, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: no toggle; end frame: true; seed: true; formats: workspace/provider format.

### Wan 2.5 — wan-2.5
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 1500 characters; prompt required: true.
- Resolutions: 480p, 720p, 1080p; duration seconds: 5, 10.
- Defaults: mode text, 5s, 1080p, 16:9, audio true. Versions: not selectable.
- text: ratios 16:9, 9:16, 1:1, input limits {"images":0,"videos":0,"audio":1,"total":1}; image: ratios from input/default, input limits {"images":1,"videos":0,"audio":1,"total":2}.
- Audio: native; end frame: false; seed: true; formats: workspace/provider format.

### Kling 2.6 Pro — kling-2.6-pro
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 2500 characters; prompt required: true.
- Resolutions: 1080p; duration seconds: 5, 10.
- Defaults: mode text, 5s, 1080p, 16:9, audio true. Versions: not selectable.
- text: ratios 16:9, 9:16, 1:1, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: optional; end frame: true; seed: false; formats: workspace/provider format.

### Veo 3.1 — veo-3.1
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 20000 characters; prompt required: true.
- Resolutions: 720p, 1080p, 4k; duration seconds: 4, 6, 8.
- Defaults: mode text, 8s, 720p, 16:9, audio true. Versions: not selectable.
- text: ratios 16:9, 9:16, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios auto, 16:9, 9:16, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: optional; end frame: false; seed: true; formats: workspace/provider format.

### HappyHorse 1.0 — happyhorse-1.0
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 2500 characters; prompt required: true.
- Resolutions: 720p, 1080p; duration seconds: 3–15, step 1.
- Defaults: mode text, 5s, 1080p, 16:9, audio false. Versions: not selectable.
- text: ratios 16:9, 9:16, 1:1, 4:3, 3:4, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: no toggle; end frame: false; seed: true; formats: workspace/provider format.

### HappyHorse 1.1 — happyhorse-1.1
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 2500 characters; prompt required: true.
- Resolutions: 720p, 1080p; duration seconds: 3–15, step 1.
- Defaults: mode text, 5s, 1080p, 16:9, audio false. Versions: not selectable.
- text: ratios 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: no toggle; end frame: false; seed: true; formats: workspace/provider format.

### Grok Imagine 1.5 — grok-imagine-1.5
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 4096 characters; prompt required: true.
- Resolutions: 480p, 720p, 1080p; duration seconds: 1–15, step 1.
- Defaults: mode text, 6s, 720p, 16:9, audio true. Versions: not selectable.
- text: ratios 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: native; end frame: false; seed: false; formats: workspace/provider format.

### H3 Max Styles — h3-max-styles
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 49868 characters; prompt required: true.
- Resolutions: 768P; duration seconds: 5–15, step 1.
- Defaults: mode text, 5s, 768P, 16:9, audio true. Versions: not selectable.
- text: ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: native; end frame: false; seed: true; formats: workspace/provider format.

### H3 Max Camera Control — h3-max-camera-control
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: image. Prompt limit: 50000 characters; prompt required: false.
- Resolutions: 480P, 768P, 1080P; duration seconds: 3–15, step 1.
- Defaults: mode image, 5s, 768P, 16:9, audio false. Versions: not selectable.
- image: ratios from input/default, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: no toggle; end frame: false; seed: true; formats: workspace/provider format.

### H3 Max Lip Sync — h3-max-lip-sync
- Workspace: https://musesparkopen.tools/ai-video-generator; operation: h3-lipsync; modes: reference. Prompt limit: 2000 characters; prompt required: false.
- Resolutions: 480P, 768P, 1080P, 2K; duration seconds: 5.
- Defaults: mode reference, 5s, 768P, adaptive, audio true. Versions: not selectable.
- reference: ratios from input/default, input limits {"images":1,"videos":0,"audio":1}.
- Audio: native; end frame: false; seed: true; formats: workspace/provider format.

### Gemini Omni — gemini-omni
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 20000 characters; prompt required: true.
- Resolutions: 720p; duration seconds: 3–10, step 1.
- Defaults: mode text, 8s, 720p, 16:9, audio true. Versions: not selectable.
- text: ratios 16:9, 9:16, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios 16:9, 9:16, input limits {"images":1,"videos":0,"audio":0,"total":1}.
- Audio: native; end frame: false; seed: false; formats: workspace/provider format.

### H3 LoRA — h3-lora
- Workspace: https://musesparkopen.tools/ai-video-generator; modes: text, image. Prompt limit: 50000 characters; prompt required: true.
- Resolutions: 480P, 768P, 2K, 4K; duration seconds: 5–15, step 1.
- Defaults: mode text, 5s, 768P, 16:9, audio true. Versions: not selectable.
- text: ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, input limits {"images":0,"videos":0,"audio":0,"total":0}; image: ratios from input/default, input limits {"images":2,"videos":0,"audio":0,"total":2}.
- Audio: native; end frame: true; seed: true; formats: workspace/provider format.

## Other integrated workflows

### ACE-Step · Fal — ace_step
- Workspace: https://musesparkopen.tools/artcraft/create-audio. Enabled: true.
- Public options: {"text_prompt_supported":true,"instrumental_toggle_supported":true,"extra_info":"60 second music generation. Provider: Fal ACE-Step."}

### Hunyuan3D V3 · Fal — hunyuan_3d_3
- Workspace: https://musesparkopen.tools/artcraft/create-object. Enabled: true.
- Public options: {"text_prompt_supported":true,"image_input_supported":true,"multi_view_supported":false,"mesh_output_types":["normal","low_poly","geometry"],"polygon_types":["triangle","quad"],"pbr_supported":true}

- Music workflow: text-to-music, 60-second output, instrumental toggle; https://musesparkopen.tools/artcraft/create-audio.
- Mesh workflow: text or one reference image to mesh; selectable options listed above; https://musesparkopen.tools/artcraft/create-object.
- World Labs Marble: marble-1.0-draft / marble-1.1 / marble-1.1-plus; prompt up to 4000 characters or image, optional panorama; stored world splats/mesh/preview according to provider result; https://musesparkopen.tools/artcraft/create-world.
- FLUX Pro Fill: owned image plus matching mask and edit prompt, PNG result, maximum 4 megapixels; https://musesparkopen.tools/artcraft/edit-image.
- Background replacement: 3–15s MP4/MOV video, prompt or image reference, 720p with original audio; https://musesparkopen.tools/artcraft/background-change.
- FLUX LoRA character training and character images: 4–20 distinct reference images, named character and trigger word, 1000-step training, then 1024×1024 PNG generation from a ready character; https://musesparkopen.tools/artcraft/characters.
- Humanize text: google/gemini-2.5-flash, up to 12000 characters, tones natural, friendly, professional, output in the input language; https://musesparkopen.tools/humanize-ai.
- Prompt Seen image-to-prompt: google/gemini-2.5-flash, one JPEG under 1 MB, tones detailed, concise, cinematic, reusable English prompt; https://musesparkopen.tools/prompt-seen.
- FilmCraft, PhotoCraft, PdfCraft, WordCraft, GridCraft, DeckCraft and browser image tools are editors, not additional paid generation models. Imported formats and export choices follow each editor. Guests edit; verified login saves/exports private AI Tasks at zero credits.

For operation reservations and settlement see [pricing.md](https://musesparkopen.tools/pricing.md). All models require validation of the actual mode, uploads and settings; the UI and server may reject unsupported combinations.