The Cleanest, Fastest Stable Diffusion WebUI.
Built for AI artists, researchers, developers, and prompt engineers. Fully open source, and no hosting required.
⭐ Star to Get Early-Supporter Perks ⭐
DreamLayer AI is an open-source Stable Diffusion WebUI that keeps the familiar Automatic1111 ⁄ Forge layout you know, replaces the clutter with a modern design system, and runs every generation step on ComfyUI in the background.
No node graph on screen, no server rental, just a lightning-fast local interface for:
- AI artists producing portfolio-ready images
- Developers and prompt engineers iterating on prompts and LoRAs
- Researchers benchmarking new models and samplers
Status: ✨ Now live: Open Alpha • Beta V1 ships: Mid-July 2025
⭐ Star the repo for updates & to get early-supporter perks
macOS:
./install_mac_dependencies.shWindows:
install_windows_dependencies.ps1macOS:
./start_dream_layer.shWindows:
start_dream_layer.bat- Frontend: http://localhost:8080
- ComfyUI: http://localhost:8188
| 🔍 Feature | 🚀 How it’s better |
|---|---|
| Familiar Layout | If you’ve used A1111 or Forge, you’ll feel at home in sec. Zero learning curve |
| Modern UX | Responsive design with light & dark themes and a clutter-free interface that lets you work faster |
| ComfyUI Engine Inside | All generation runs on a proven, modular, stable ComfyUI backend. Ready for custom nodes and advanced hacks |
| Closed-Source Model Support | One-click swap to GPT-4o Image, Ideogram V3, Runway Gen-4, Recraft V3, and more |
| Local first | Runs entirely on your GPU with no hosting fees, full privacy, and instant acceleration out of the box |
- Python 3.8+
- Node.js 16+
- 8GB+ RAM recommended
DreamLayer ships without weights to keep the download small. You have two ways to add models:
DreamLayer can also call external APIs (OpenAI DALL·E, Flux, Ideogram).
To enable them:
Edit your .env file at dream_layer/.env:
OPENAI_API_KEY=sk-...
BFL_API_KEY=flux-...
IDEOGRAM_API_KEY=id-...Once a key is present, the model becomes visible in the dropdown. No key = feature stays hidden.
Step 1: Download .safetensors or .ckpt files from:
- Hugging Face
- Civitai
- Your own training runs
Step 2: Place the models in the appropriate folders (auto-created on first run):
- Checkpoints/ → # full checkpoints (.safetensors)
- Lora/ → # LoRA & LoCon files
- ControlNet/ → # ControlNet models
- VAE/ → # optional VAEs
Step 3: Click Settings ▸ Refresh Model List in the UI — the models appear in dropdowns.
Tip: Use symbolic links if your checkpoints live on another drive.
The installation scripts will automatically install all dependencies and set up the environment.
Starring helps us trend on GitHub which brings more contributors and faster features.
Early stargazers get perks:
- GitHub Hall of Fame: Your handle listed forever in the README under Founding Supporter
- Early Builds: Download private binaries before everyone else
- Community first hiring: We prioritize contributors and stargazers for all freelance, full-time, and AI artist or engineering roles.
- Closed Beta Invites: Give feedback that shapes 1.0
- Discord badge: Exclusive Founding Supporter role
⭐ Hit the star button right now and join us at the ground floor
☺️
- Star this repository.
- Watch releases for the July code drop.
- Join the Discord (link coming soon) and say hi.
- Open issues for ideas or feedback & Submit PRs once the code is live
- Share the screenshot on X ⁄ Twitter with
#DreamLayerAIto spread the word.
All contributions code, docs, art, tutorials—are welcome!
- Create a PR and follow the evidence requirements in the template.
- See CHANGELOG Guidelines for detailed contribution process.
Full docs will ship with the first code release.
DreamLayer AI will ship under the GPL-3.0 license when the code is released.
All trademarks and closed-source models referenced belong to their respective owners.
### Made with ❤️ by builders, for builders • See you in July 2025!