AI 图像/视频生成排行

If your image was a pizza and the CFG the temperature of your oven: this is a thermostat that ensures it is always cooked like you want. Also adds a 30% speed increase. For ComfyUI / StableDiffusion

A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.

Tiled samplers for ComfyUI

A collection of one-click self-hosted AI

An SDK/Python library for Automatic 1111 to run state-of-the-art diffusion models

Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.

Stable Diffusion Houdini Toolset

Better version for BiRefNet in ComfyUI | Both img & video

attention map tools for huggingface/diffusers

Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"

Extension for Automatic1111 and ComfyUI to automatically create masks for Background/Hair/Body/Face/Clothes in Img2Img

Stable Diffusion Browser for Windows, Mac, and Linux

SD-WEBUI-DISCORD is a Discord bot developed in Go language for stable-diffusion-webui. It utilizes the sd-webui-go to invoke the sd-webui API and supports cluster deployment of multiple sd-webui nodes with automatic scheduling and allocation.

Make use of Intel Arc Series GPU to Run Ollama, StableDiffusion, Whisper and Open WebUI, for image generation, speech recognition and interaction with Large Language Models (LLM).

Animation via tick. Wave-based parameter modulation, Math operations with Unary and Binary support, universal Value conversion for all major types (int, string, list, dict, Image, Mask), shape masking, image channel ops, batch processing, dynamic bus routing. Queue & Load from URLs.

cutoff implementation for ComfyUI

[CVPR 2024] "MACE: Mass Concept Erasure in Diffusion Models" (Official Implementation)

Agent-friendly ComfyUI workflow skills for OpenClaw, Hermes Agent, Codex, and Claude Code; complementary to Comfy official local MCP.

Learn to serve Stable Diffusion models on cloud infrastructure at scale. This Lightning App shows load-balancing, orchestrating, pre-provisioning, dynamic batching, GPU-inference, micro-services working together via the Lightning Apps framework.

Official code base for MinD-Video