reproduction of AnimateAnyone

fastblend for comfyui, and other nodes that I write for generate video. rebatch image, my openpose

Differential Diffusion: Giving Each Pixel its strength

Go module to build ComfyUI workflow programmatically

Nodes for better inpainting with ComfyUI: Fooocus inpaint model for SDXL, LaMa, MAT, and various other tools for pre-filling inpaint & outpaint areas.

docker setup for a gradio based version of video retalking (audio-based lip sync solution)

Codes for ID-Specific Video Customized Diffusion

This repo is a packaged version of the Yolov9 model.

Directed Diffusion: Direct Control of Object Placement through Attention Guidance (AAAI2024)

Addon for Blender that lets you generate lipsync animation automatically from audio files.

MotionDirector Training For AnimateDiff. Train a MotionLoRA and run it on any compatible AnimateDiff UI.

ComfyUI wrapper node for original freecontrol diffusers implementation

Unofficial implementation of BRIA RMBG Model for ComfyUI

An assortment of ComfyUI Nodes that are a Work in Progress

ComfyUI API Workflow Dependency Graph

The official implementation of Latte: Latent Diffusion Transformer for Video Generation.

OneTrainer is a one-stop solution for all your stable diffusion training needs.

DARK_GLIGEN GUI using ComfyUI on the backend

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

Rescale the CFG per channel at each step to aim towards a desired final intensity

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

ComfyUI nodes for training AnimateDiff motion loras

Code release for "InstanceDiffusion: Instance-level Control for Image Generation"

Instant voice cloning by MyShell.

Official repo of Generative Models: What do they know? Do they know things? Let's find out!

Code for ICLR 2024 paper "Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators"

built upon the Würstchen architecture and its main difference to other models, like Stable Diffusion

Distribute and run LLMs with a single file.

Next generation face swapper and enhancer

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.