AI 图像/视频生成排行

[Arxiv 2023] img2img version of stable diffusion. Line Art Automatic Coloring. Anime Character Remix. Style Transfer.

all ComfyUI http/ws APIs. support NodeJS / Browser environments. and advanced programmable workflow.

[CVPR'25-Demo] Official repository of "TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models".

TBG Enhanced Tiled Upscaler and Refiner upscales up to 200MP with precise control. It features dual-model processing (structure + detail), per-pixel denoising to control where creativity is applied, and per-tile and per-object prompts, denoise, and seeds. Advanced fast previews. New generative tile fusion seamless joining, even on high-denoise.

Adaptation of the merging method described in the paper - Git Re-Basin: Merging Models modulo Permutation Symmetries (https://arxiv.org/abs/2209.04836) for Stable Diffusion

GPTs for ComfyUI | Explanation Creation Resolution | ComfyUI 助手

Dreambooth implementation based on Stable Diffusion with minimal code.

Stable Diffusion Docker image preconfigured for usage with AMD Radeon cards

A lightweight Gradio WebUI for stable-diffusion.cpp.

Documents repo of ForkSilly. ForkSilly：兼容sillytavern（酒馆）角色卡、世界书、正则、预设、聊天记录的安卓移动端应用；同时也可作为stable diffusion客户端使用。

A versatile multi-modal chat application that enables users to develop custom agents, create images, leverage visual recognition, and engage in voice interactions. It integrates seamlessly with local LLMs and commercial models like OpenAI, Gemini, Perplexity, and Claude, and allows to converse with uploaded documents and websites.

1-shot image segmentation using Stable Diffusion

ComfyUI TCD implementation

Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models (ICLR 2024)

(CVPR 2024) 🧩 TokenCompose: Text-to-Image Diffusion with Token-level Supervision

PWA Web App front end for Stable Diffusion, on React/NextJS with Material UI

A Gimp plugin that brings StableDiffusion functionality via Automatic1111's API

A minimal implementation of a denoising diffusion model in PyTorch.

ComfyUI Depth Anything (v1/v2/v3/distill-any-depth) Tensorrt Custom Node (up to 14x faster) ⚡

It's an AI Tag (Prompt) generator for magic drawer! We have many tags and support to generate prompts easily!