Deforum is a free Stable Diffusion tool for artists and developers who want to generate images and animations on their own hardware. The project is no longer maintained. Its code uses MIT, while downloaded Stable Diffusion models retain their own weight licenses. Its Python script and Jupyter notebook support local generation, while Google Colab and Replicate offer cloud execution.
Animation is its main focus. It supports interpolation, 2D and 3D animation, and RANSAC animation. CLIP, aesthetic, and color palette conditioning give users ways to influence the appearance of generated images beyond the prompt. The inference notebook exposes detailed controls for prompts and generation settings, so it suits people who want to experiment with their output.
The notebook format is a defining part of the experience. Deforum was designed around Google Colab, but it also works in Jupyter Lab or Jupyter Notebook on a local machine. Developers can modify its Python implementation for custom workflows and pipelines. Local execution uses NVIDIA GPUs through CUDA, and some automatic model downloads require a Hugging Face account token.
Where generation runs depends on the runtime you choose: local Python and Jupyter use your machine, while Colab's hosted runtime and Replicate use cloud servers. Colab can also connect to a local runtime. Replicate provides a web demo and an API.
Claim this page and we'll verify you by hand. Deforum gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Deforum?Promote it
Something wrong or outdated on this page?
4.8KUpdated 3 weeks agoApache-2.0
macOS · Windows · Linux · Docker · Web#GGUF#Hugging Face integration#llama.cpp backend
Lollms WebUI is a local, single-user AI interface for people who want text chat and media generation in one place. It runs on Windows, macOS and Linux, with Docker support, and lets writers, developers and other users choose models and task-specific personalities. It's free and open source under Apache 2.0. The project receives minimal maintenance.
135.6KUpdated 48 minutes agoGPL-3.0
macOS · Windows · Linux · Web#ControlNet#Inpainting#LoRA
7.3KUpdated 1 week agoApache-2.0
macOS · Windows · Linux · Docker · Web#ControlNet#Image-to-image#Inpainting
4.6KUpdated 20 hours agoMIT
macOS · Windows · Linux · Docker · Web#Visual workflows
SwarmUI is a self-hosted AI image generation interface that combines a straightforward generation screen with direct access to ComfyUI's node-based workflows. It's for people who want to run creative models on their own hardware, with room to build more detailed workflows as their needs grow.
77KUpdated 21 hours agoApache-2.0
macOS · Windows · Linux · Docker · Web#Code execution#GGUF#Image-to-image
9.7KUpdated 1 day ago
macOS · Windows · Linux · Docker · Web#Batch processing#ControlNet#GGUF
ComfyUI is a local visual AI workspace for artists and technical teams who want to control how images, video, audio, 3D models and text are made. Its node canvas shows each model and processing step, so users can build and adjust workflows without writing code. It runs on your hardware.
SD.Next is a self-hosted web interface for artists, researchers and people who want to generate and edit images or videos on their own hardware. It builds on Automatic1111 WebUI's original codebase and supports Stable Diffusion alongside other diffusion models. It's open source under Apache 2.0.
Unsloth brings model training and everyday AI use into a desktop app for people who want to run models on their own hardware. Its no-code interface covers chat, fine-tuning and media generation on macOS, Windows and Linux. The Unsloth software is open source under Apache 2.0.
Wan2GP brings video, image, music and speech generation to your own computer, with particular attention to GPUs with limited memory. It's for creators who want several media models in one browser interface. The project builds on Wan-Video/Wan2.1.