#image-generation Repositories
288 repositories total
Dynamic Thresholding (CFG Scale Fix) for Stable Diffusion (SwarmUI, ComfyUI, and Auto WebUI)
Automatically find issues in image datasets and practice data-centric computer vision.
something like visual-chatgpt, the open-source version of Wenyiyan
[ICLR24] Official implementation of the paper โMagicDrive: Street View Generation with Diverse 3D Geometry Controlโ
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
Official PyTorch implementation of "VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization" (CVPR 2021)
[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process
Pose, outfit & portrait reference library with Chinese and English prompts, plus in-browser AI try-on
Seamlessly extend any image in any direction with AI. Open-source web app powered by Gemini via OpenRouter, with Poisson-blended seams and best-of-3 variant picker.
660+ muapi-hosted generative media models plus community-submitted third-party API tools (SEO, enrichment, social, scraping) โ one YAML file per entry, browsable by capability.
Scenario for Blender: AI images, video, 3D, and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later.
AI PC starter app for doing AI image creation, image stylizing, and chatbot on a PC powered by an Intelยฎ Arcโข GPU.
The official starter kit for the Nano Banana Hackathon. Clone this repo to get building fast!
ControlNet scheduling and masking nodes with sliding context support
๐ฌ Generate images from any camera viewpoint via 3D interactive control. Drag the camera in 3D space or use sliders to set azimuth/elevation/distance, then generate. Built with Three.js + Gradio, bilingual ZH/EN UI.
An all-in-one, 100% local AI video, image, and music studio. Director mode plans full music videos and short films from a single prompt. Built on the WanGP pipeline. Install via Pinokio.
[SIGGRAPH'22] StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
๐จ Open-source AI slide studio inside Codex: image-native decks, every slide a full visual canvas. โก 10+ high-quality slides in ~4โ5 minutes โ Fast mode renders every page in parallel. ๐ Watch the whole chain live: research โ outline โ style โ render โ edit โ present โ export PDF/PPTX. ๐ฅ๏ธ Browser-first ยท zero API keys ยท durable projects.
:fire: :fire: :fire: A paper list of some recent Computer Vision(CV) works
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
Local-first, agent-native control plane for ComfyUI โ MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in natural language on ANY LLM (Claude, ChatGPT, Gemini, offline Ollama, or any hosted model). 178 tools, 36 AI skills, 55 installer packs. Local, LAN, VPS, or Comfy Cloud.
Local-First AI Workflow WebUI for Gemini, integrating multimodal chat, Canvas, file handling, real-time search, code execution, and advanced reasoning.
Zizi Animation - Fully free AIGC video generation software, mainly used for AI short dramas, AI movies, novel tweets
Official PyTorch implementation for the paper High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions (ECCV 2022).
Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.
Text to image app. Suitable for long image push articles for WeChat Official Accounts and image post creation for social media like Xiaohongshu, Instagram, etc.
Plug-and-play JSON style prompts for Nano Banana Pro, GPT Image & Midjourney. Copy one style.json, get a consistent look. New styles every week.
Flatkey media generation CLI for images, videos, audio, text, credits, and model discovery.
[CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation
[ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!
[Extended version ICLR 2025 Blog Track] Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation
FreeTheAi (Free The AI): free OpenAI-compatible AI API with 50+ models, Discord key signup, streaming, tools, images, Messages, and Responses. No credit card.
OpenโWebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15 specialized tools, function pipelines, and filters, this project supports academic research, agentic autonomy, multimodal creativity, workflows, and more.