Explore Projects
Discover 366 open source projects
Showing 301-320 of 366 projects
declare-lab/tango
A family of diffusion models for text-to-audio generation, targeting vibe coders who build with AI tools.
alibaba/Tora
A diffusion-based video generation model for trajectory-oriented video synthesis.
XiangLi1999/Diffusion-LM
Diffusion-LM is a Python library for training and using large language models with diffusion models.
Francis-Rings/StableAvatar
StableAvatar is an end-to-end video diffusion transformer that generates high-quality audio-driven avatar videos.
Tencent-Hunyuan/HunyuanCustom
A multimodal-driven architecture for customized video generation, enabling developers to create unique AI-powered videos.
benrugg/AI-Render
A Python library that integrates Stable Diffusion with the Blender 3D modeling software for AI-powered 3D content creation.
6174/comflowy
An open-source platform for building AI-powered tools and applications using ComfyUI and Stable Diffusion.
wfjsw/danbooru-diffusion-prompt-builder
A tool for building prompts for Danbooru and NovelAI image generation, leveraging TypeScript and Vue.js.
DreamLM/Dream
Dream 7B is a large diffusion language model that enables advanced AI-powered text generation and editing capabilities.
shallowdream204/DreamClear
A high-capacity image restoration model focused on privacy-safe dataset curation for AI-powered tooling.
ali-vilab/UniAnimate
UniAnimate is a Python library for generating consistent human image animation using unified video diffusion models.
Suzie1/ComfyUI_Comfyroll_CustomNodes
Custom nodes for SDXL and SD1.5 including Multi-ControlNet, LoRA, Aspect Ratio, and more.
buoyancy99/diffusion-forcing
This repository contains code for a research paper on a new diffusion-based text generation model.
soulteary/docker-prompt-generator
A tool that uses machine learning models to generate prompts for AI image generation apps like Midjourney and Stable Diffusion.
hako-mikan/sd-webui-lora-block-weight
A Python library that adds a 'LoRA' block to the Stable Diffusion web UI for customizing model weights.
cure-lab/MagicDrive
Official implementation of a paper on street view generation with diverse 3D geometry control.
ChenyangQiQi/FateZero
FateZero is a video editing tool that uses AI-powered text-driven video editing and style transfer.
showlab/Show-1
A text-to-video generation model that combines pixel-level and latent diffusion approaches.
cloneofsimo/minDiffusion
Minimalistic PyTorch implementation of diffusion models, a powerful class of generative AI models.
isekaidev/stable.art
Photoshop plugin for generating AI-powered art with Stable Diffusion and Automatic1111 backend.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.