A collection of ControlNet poses

a self-hosted webui for 30+ generative ai

Docker image for Stable Diffusion WebUI with ControlNet, After Detailer, Dreambooth, Deforum and ReActor extensions, as well as Kohya_ss and ComfyUI

This repo implements ControlNet with DDPM and Latent Diffusion Model in PyTorch with canny edges as conditional control for Mnist and CelebHQ

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

collection of diffusion model papers categorized by their subareas

Stable Diffusion Sketch, an Android client app that connect to your own automatic1111's Stable Diffusion Web UI

Transform your simple scribbles into architectural designs using style transfer with Stable Diffusion, LCM, IP Adapters and ControlNet. Scribble Architect combines creativity with generative AI technology, improving the inspiration process.

Always focus on prompting and generating

Docker image for Stable Diffusion WebUI with ControlNet, After Detailer, Deforum and ReActor extensions

[SIGGRAPH 2024] "EASI-Tex: Edge-Aware Mesh Texturing from Single Image", ACM Transactions on Graphics.

diffusers for CoreML

Wunjo CE: Face Swap, Lip Sync, Control Remove Objects & Text & Background, Restyling, Audio Separator, Clone Voice, Video Generation. Open Source, Local & Free.

Python SDK for Novita AI API (Txt2Img, Img2Img, Txt2Video, Img2Video, Doodle, Remove Background, Replace Object, Reimagine, Merge Faces, ControlNet, VAE, LoRA)

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

Docker image for Stable Diffusion WebUI Forge

An implementation of ControlNet as described in "Adding Conditional Control to Text-to-Image Diffusion Models" published by Zhang et al.

StyleAligned enables zero-shot style alignment in Text-to-Image (T2I) models using minimal attention sharing, ensuring consistent style transfer without fine-tuning.