ArtCraft launches an AI image and video creation IDE
ArtCraft, which appeared on GitHub Trending, describes itself as an "intentional crafting engine" for artists, designers and filmmakers, and an IDE for interactive AI image and video creation. It combines 2D compositing, 3D scene staging, character posing and identity transfer, image-to-3D mesh and background removal with text-to-image, prompted image editing and image-to-video flows, letting users pick their own models. Its listed catalog totals 62 models — 16 image, 25 video, 5 music and sound, 11 3D mesh and 5 world/Gaussian-splat models — with integrations including Grok, Midjourney, Sora and World Labs Marble; some entries are marked disabled or restricted, and Kling, Google, Runway and Luma integrations are listed as planned.
Why it matters: It illustrates how multi-model creative tools are moving from chat-style prompting toward visual, repeatable composition workflows.
ArtCraft is an intentional crafting engine for artists, designers, and filmmakers
ArtCraft
The IDE for artists.
https://github.com/user-attachments/assets/7339bd09-3e0d-44a7-a024-af9de64e4c11
Watch the two-minute ArtCraft demo on YouTube
Download ArtCraft · GitHub releases · Build from source
ArtCraft is the IDE for interactive AI image and video creation. Compose in 2D, stage scenes in 3D, and choose the models that fit your work. Turn prompting into crafting with visual tools for precise, repeatable results.
Show, Don't Tell: Advanced Crafting Features
Artists need control over composition, character identity, and camera placement. Build the scene before you generate it. Click any preview to view it at full size.
| Feature | Preview |
|---|---|
| Image to Location Place virtual actors in a consistent environment and plan multiple shots in the same room. |
|
| 3D Image Compositing Layer backdrops, foregrounds, and props in 3D to build compositions with depth. |
|
| 2D Image Compositing Compose a scene with image layers, background removal, and drawing tools. |
|
| Image to 3D Mesh Turn an image into a 3D object you can position, rotate, and frame precisely. |
|
| Character Posing Pose characters and set your camera before generating the final shot. |
 |
| Scene Blocking with Kitbashing Combine 3D asset kits to control camera angles, object placement, and depth. |
|
| Character Identity Transfer Use a posed mannequin to guide the placement and pose of your character. |
|
| Background Removal Isolate subjects to use as props, layers, or backdrops in 2D and 3D scenes. |
|
| Mixed Asset Crafting Combine image cutouts, worlds, and 3D meshes in one scene. |
 |
More previews are coming for scene blocking, canvas editing, and scene relighting.
Quick and Easy Prompting
Start with a prompt when you want to explore an idea quickly, then use the canvas and scene tools to refine it.
| Feature | Preview |
|---|---|
| Text to Image Explore ideas across a wide range of image models with a text prompt. |
|
| Prompted Image Editing Describe changes to an image with models such as Nano Banana Pro and GPT Image. |
|
| Canvas Image Editing Use drawing, masks, and inpainting to guide exactly where an image changes. |
|
| Image to Video Animate an image with your choice of video models and generation controls. |
More previews are coming for image inpainting and image ingredients.
Models and Providers Supported within ArtCraft
| Provider | Models and workflows |
|---|---|
| ArtCraft | Images, video, music and sound, 3D meshes, and worlds. Browse the complete model catalog below. |
| Grok | Grok Imagine and Grok Video. |
| Midjourney | Midjourney image generation. |
| Sora | Sora 1, Sora 2, and GPT Image 1. |
| World Labs | Marble world generation with Gaussian splats. |
† Currently disabled. ‡ Restricted model; not currently available in the desktop app.
Images (16)
| Family | Models |
|---|---|
| Nano Banana | Nano Banana; Nano Banana 2; Nano Banana Pro |
| GPT Image | GPT Image 1.5; GPT Image 2; GPT Image 2.5 Flare; GPT Image 2.5 Sunburst |
| FLUX | FLUX.1 [dev]; FLUX.1 [schnell]; FLUX 1.1 [pro]; FLUX 1.1 [pro] ultra |
| Seedream | Seedream 4; Seedream 4.5; Seedream 5 Lite; Seedream 5.0 Pro; Seedream 5.0 Pro Ultra |
Video (25)
| Family | Models |
|---|---|
| Seedance | Seedance 1.0 Lite †; Seedance 1.5 Pro; Seedance 2.0 |
| Kling | Kling 1.6 Pro; Kling 2.1 Pro †; Kling 2.1 Master †; Kling 2.5 Turbo Pro; Kling 2.6 Pro; Kling 3.0 Pro †; Kling 3.0 Standard † |
| Veo | Veo 2 †; Veo 3 †; Veo 3 Fast; Veo 3.1; Veo 3.1 Fast; Veo 3.1 Lite |
| Sora | Sora 2 †; Sora 2 Pro † |
| Vidu | Vidu Q3; Vidu Q3 Turbo |
| MiniMax | MiniMax H3; MiniMax H3 Turbo ‡; MiniMax H3 Ultra ‡ |
| Flux | Flux 3; Flux 3 Draft |
Music and sound (5)
| Family | Models |
|---|---|
| Suno | Suno Music; Suno Remix; Suno Sounds; Suno Sample |
| Seed Audio | Seed Audio 1.0 |
3D meshes (11)
| Family | Models |
|---|---|
| Hunyuan 3D | Hunyuan 3D 2.0; Hunyuan 3D 2.1; Hunyuan 3D 3; Hunyuan 3D 3 Sketch; Hunyuan 3D 3.1 Pro; Hunyuan 3D 3.1 Rapid; Hunyuan 3D 3.1 Part; Hunyuan 3D 3.1 Smart Topology |
| Tripo3D | Tripo3D H3.1 |
| Meshy | Meshy 6 |
| Rodin | Rodin 2.5 Fast |
Worlds and Gaussian splats (5)
| Family | Models |
|---|---|
| Marble | Marble 1.0; Marble 1.0 Draft; Marble 1.1; Marble 1.1 Plus |
| TripoSplat | TripoSplat |
Additional provider integrations are planned for Kling, Google, Runway, and Luma. We're also interested in supporting existing subscriptions with aggregators such as OpenArt and Freepik.
Downloads
Documentation
How we got here
- Manus community invites users to host Manus 2.0 meetups with attendee creditsManus · Luma
- AI is rewriting video editing workflows — and who gets to call themselves a pro钛媒体 · Runway
- Midjourney tests a 'thinking mode' for image generation on its Alpha siteMidjourney · Midjourney
- SpaceXAI backs Omarchy with $1.5M in Grok tokens as founding patronThe Verge AI · Grok
- Europe's Q3 venture funding hits $25B, a four-year high, with AI taking 75%Techmeme · World Labs
- Jensen Huang 'MJ world tour' AI meme videos flood Bilibili, spotlighting Chinese video models36氪 人工智能 · Runway