modelscope/DiffSynth-Studio
open-source diffusion engine for AI image and video generation
View on index · View in 3D Map
Related repos
- Open source toolkit for training diffusion image models with a simple web or command line interface—supports latest models, requires high-end Nvidia GPU
- Scans your AI-generated images, grabs all the metadata and workflow info, and lets you search, tag, and organize everything—handy for keeping track of your Stable Diffusion creations
- AI image generation toolkit using Stable Diffusion models
- library for speeding up diffusion models
- Curated list of video diffusion model projects, papers, and resources for generation, editing, and related tasks
- Agentic framework for video editing
- control diffusion models with extra conditions for image generation
- diffusion models for generating images, audio, and 3D with easy pipelines
- Scripts and tools for training and fine-tuning Stable Diffusion models
- Training large-scale diffusion models on a budget
