storytold/artcraft

ArtCraft is an intentional crafting engine for artists, designers, and filmmakers

What it solves

ArtCraft addresses the lack of precise control in AI-generated art. Instead of relying solely on text prompts, which can be unpredictable, it provides a visual environment where artists can plan compositions, stage scenes, and maintain character consistency across multiple shots.

How it works

It functions as an Integrated Development Environment (IDE) for AI creation, combining 2D and 3D tools with a wide array of generative models. Users can build a scene using 3D meshes, kitbashing, and image layers to define the layout and camera angles before triggering the final AI generation. It integrates with various providers (including Midjourney, Sora, and World Labs) and its own catalog of over 60 models for images, video, audio, and 3D assets.

Who it’s for

Digital artists, concept artists, and creators who need professional-grade control over composition, character identity, and spatial arrangement in AI-generated imagery and video.

Highlights

  • 3D Scene Staging: Use 3D image compositing, image-to-3D mesh conversion, and kitbashing to block scenes and set camera placement.
  • Character Control: Features for character posing and identity transfer using mannequins to guide the AI.
  • Multi-Modal Integration: Supports a vast library of models for text-to-image, image-to-video, music, sound, and Gaussian splats.
  • Hybrid Editing: Combines traditional canvas tools (masks, inpainting, drawing) with prompted image editing.

Written about in

Related

  • Project
    GML-MMGroup/AdCraft

    AdCraft is an open‑source AI‑driven platform that converts a textual brief into a complete, editable advertising video. It orchestrates specialised agents (script, visuals, characters, scenes, storyboard, video, sound, compositing) and stores every generated asset in a unified library, allowing fine‑grained revisions via chat or canvas edits. The system supports multiple image/video/audio models, provides reusable character/scene libraries, and even can clone the structure of an existing commercial to produce a new ad with your own product and style.

  • Project
    tigerowo/infinite-canvas

    An open-source multimodal AI creative workbench that combines an infinite canvas with AI image, video, and audio generation tools to streamline visual iteration.

  • Project
    pixel-point/toolcraft

    Toolcraft is a free, MIT‑licensed starter kit that combines React, Tailwind, and a ready‑made canvas/UI library to let AI coding agents (Codex, Claude, Cursor, etc.) generate custom web‑based design tools in minutes.

  • Project
    storytold/deckcraft

    DeckCraft is an open‑source, Rust‑based PowerPoint‑compatible presentation editor that runs on desktop OSes and the web, supports rich slide authoring, media, animations, and offers a CLI/MCP control channel for scripting or AI agents.

  • Project
    VisionDepth/VisionDepth3D

    VisionDepth 3D is a Windows desktop app that converts 2‑D images or videos into stereoscopic 3‑D using AI depth models, depth‑map blending, RIFE frame‑interpolation, and AI super‑resolution. It offers a free tier (limited length, 1080p, watermarked) and a one‑time $59.99 Pro tier (no limits, 4K+, batch processing, advanced controls). Installation is via an Itch.io “Setup Hub” that provides CUDA (NVIDIA) or DirectML (AMD/Intel) builds. The software is proprietary, but the AI models it downloads are open‑source under their own licenses.