A Gradio-based web UI for running Stable Diffusion and newer image/video models, continuing the Forge fork with added model support and optimizations.
Open-source alternative to:Midjourney
Forge Neo is a web interface for generating images and videos with Stable Diffusion and related diffusion models. It is a fork of the Stable Diffusion WebUI Forge platform, continued from the last Gradio 4.40.0-based release of Forge and focused on optimization and usability through a browser-based GUI.
The project adds support for a range of recent models, including Qwen-Image, Flux.2-Klein, Z-Image, Wan 2.2 (14B), Krea 2, Anima, and Ernie-Image, along with ControlNet variants such as LLLite, Union and Region. It also includes multiple attention backends (SageAttention, FlashAttention, xformers, PyTorch), tiled VAE, torch.compile support, and a rewritten preset system that stores checkpoint and parameter selections.
Installation runs through a launch script, with optional uv-based package installation and command-line flags for memory management, model directory sharing with other UIs, and API access. Video export requires FFmpeg.
Summary generated by AI from the project's README. GitHub stats refresh daily.
A node-graph GUI, API and backend for running diffusion models locally to generate images, video, audio and 3D content.
Open-source Stable Diffusion-based tool for generating character-consistent comic images and long-range image-to-video sequences.
Offline, open-source image generator built on Stable Diffusion XL that lets you focus on prompts instead of manual parameter tuning.
A web-based creative engine for generating and editing images with Stable Diffusion and other AI models, featuring a unified canvas and node-based workflows.
Open-source large-scale video generative models for text-to-video, image-to-video, speech-to-video and character animation.
A serving framework that extends vLLM to run omni-modality models producing text, image, audio, video and action outputs.