a self-hosted webui for 30+ generative ai

A tab for sd-webui for replacing objects in pictures or videos using detection prompt

Craft your visions

ControlAnimate Library

Generate a video that morphs between subjects, with an optional style

This node creates a sequence of frames by moving and scaling a subject image over a background image.

A serverless application that uses AnimateDiff to run a Text-to-Video task on RunPod.

Smooth and stabilise OpenPose in ComfyUI: removes pose jitter, hand flicker and dropped keypoints before ControlNet

Fully local, standalone AI creative studio: local LLM chat (GGUF, no Ollama), text-to-image (SD1.5/SDXL) and text-to-video (AnimateDiff). FastAPI + React. Runs offline on a 6GB GPU.

An environment where you can easily generate videos on your local PC using AnimateDiff prompt travel

Seamlessly tiling video style transfer in ComfyUI — IPAdapter + dual ControlNet + AnimateDiff. Re-skins photographed footage while keeping architecture and camera motion. Built for 4-wall projection.

Create short, vibrant animated GIFs with the AnimateDiff model on Tenstorrent hardware.

Hybrid Image - Video creator

🎬 AI生成的动漫短片展示

AI Animation — animatediff, live2d ai, ai character animation, viggle tutorial.

Text-to-video generation application that converts natural language (english) prompts into short animated videos using diffusion models and AnimateDiff, with GPU-aware optimization and an interactive Gradio UI that can be executed on Google Colab (T4 GPU).

AI-powered media processing platform using React, FastAPI, asynchronous workers, and GPU-based inference pipelines.

Configurable multi-stage pipeline for synthetic identity media — SDXL images, IP-Adapter identity conditioning, AnimateDiff video, and talking video with TTS. Runs on 6 GB VRAM with NF4 quantization and flash attention.