Top AI Project by Categories

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025 Oral)

Seamlessly integrate state-of-the-art transformer models into robotics stacks

Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization

Code for FreeScale, a tuning-free method for higher-resolution visual generation

Processes SafeTensors files for Stable Diffusion 1.5 (SD 1.5), Stable Diffusion XL (SDXL), and FLUX models. It extracts the UNet into a separate file and creates a new file with the remaining model components (without the UNet).

This repository contains the implementation for the paper "AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA", accepted by ICML 2024.

PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage

📊 Research-focused SDXL training framework exploring novel optimization approaches. Goals include enhanced image quality, training stability & comprehensive monitoring. ⭐ Performance-focused research framework.

Stable Diffusion XL LoRa Training

comfyUI+vscode，两大神器首次跨界融合。集成式AGI大模型开发+AIGC创意平台,苹果OOTB模式,解压即用。comfyUI+vscode， The first cross-border fusion of two major artifacts. Integrated AGI Large Model Development +AIGC Creative Platform, Apple OOTB mode, ready to use for decompression.

Script that generates TikTok style videos using ffmpeg, moviepy, chatGPT, and SDXL api within a minute

ComfyUI Nodes - Get the colors palette from image

Shuffle GPT-2's layers and have it prompt an image. Node works with any model - Flux, SD3, SDXL...

Continuous progress in AI research leads to the development of more robust algorithms, models, and techniques, making AI solutions more effective and reliable.

SUPIR upscaling wrapper for Forge Webui

Docker image for ComfyUI: The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

A collection of Stable Diffusion Templates that will allow you to use best UIs with the best checkpoints and significantly reduce the time needed to get started.

InvokeAI-Colab provides a simple setup to run the InvokeAI (Stable Diffusion) model on Google Colab. This repository allows users to quickly generate AI art by leveraging the power of cloud computing without needing a high-end local setup. It includes setup instructions and necessary scripts for seamless integration.

Simple containerized Stable Diffusion/A1111/Forge/ComfyUI install.

Don't forgot to star the Repository

It helps users interact with multiple AI models directly through Telegram, particularly large language models like DeepSeek-R1, Claude, GPT, Grok, Cohere, DALL.E, SDXL, Llama 3.3, and Mistral.

At your own risk, SDXL safetensors to Diffusers.

sd-test-prompts .. some predefined prompts for A1111/Forge Stable Diffusion WebUI to test options

A notebook created for training StableTTS models in Google Colab easily!

The Official Github repo of OdysseyXL

Telegram based improvements while using fooocus on mobile over network

Generate batches of SDXL images

PromptGlow takes a bare bones prompt and attempts to create a prompt optimized for Flux.

Generate AI images directly in Minecraft!

task for superteams.ai

Ipynb for Stable Diffusion Web UI run on Google Colab

Stable diffusion offline txt2img program made with python tkinter gui library.

WebUI, the new way to make the web.