Spirit Lora Trainer is a robust toolkit for training Flux1-LoRA models with a focus on simplicity and reliability and based on kohya-ss script. 智灵训练器.

Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!

For SDXL, SD1.5, Flux. Nuke T5 and let CLIP guide Flux.1 on its own! Or let let random guide Flux.1! Or load a CLIP crazy opinion embedding about your image and let that guide the AI!

run flux1/sd3 model with beginner GPU (low cost) or even CPU

flux1非官方的量化模型(flux1 unofficial quantize model)

An AI powered photobooth for your next profile picture

Easy local FLUX.1 Inference

Comfy Nodes (and a CLI script) for shuffling around layers in transformer models, creating a curious confusion.

WebUI for running Flux LoRAs using the Replicate API.

ImageGen MCP Server

ComfyDL is a robust Command Line Interface (CLI) tool for downloading models for ComfyUI. It automates the process of fetching models from various sources (like Hugging Face, Civitai) and placing them into the correct directories within your ComfyUI installation.

The Private AI Setup Dream Guide for Demos automates the installation of the software needed for a local private AI setup, utilizing AI models (LLMs and diffusion models) for use cases such as general assistance, business ideas, coding, image generation, systems administration, marketing, planning, and more.

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

Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!

A ComfyUI custom node suite to augment the capabilities of Open Creative Studio

An AI image generation desktop app utilizing the Flux.1 model, dev’ and ‘schnell’ variants, served by DeepInfra. Developed using Python Flet, the app is currently compatible with macOS only and requires an API key from DeepInfra.

AI Chat and AI Images Using OpenAI and Flux 1 from Pollinate AI

Complete end-to-end workflow for generating 3D models from text prompts using FLUX.1 and TRELLIS models.

A version of Neo-Forge WebUI which supports Linux. Forked from or based on: https://github.com/Haoming02/sd-webui-forge-classic

Generate high-quality images using FLUX.2 [dev], a 32B parameter rectified flow model by Black Forest Labs.

Generate stunning images from text prompts using FLUX.1 [dev], a 12B parameter rectified flow transformer guidance-distilled from FLUX.1 [pro].

Automated setup for ComfyUI on Windows with CUDA, custom plugins, and optimized PyTorch settings. Made to Run as Server and Error Correct,. Easy installation and launch using Miniconda.

FluxPipeline is a prototype experimental project that provides a framework for working with the FLUX.1-schnell image generation model. This project is intended for educational and experimental purposes only.

Art Style Fusion Prompt Engineering is a Gradio app that blends art styles, descriptions, and artist recommendations into prompts for T5 text encoders (Tested Heavily with Flux)

SmartAgent Bot is an AI-powered Telegram bot built using n8n workflows and Google Gemini models. It processes both text and voice messages, intelligently routing requests to specialized AI agents for email, calendar, stock data, growth analytics, prompt generation, or image creation. The bot logs interactions in Google Sheets,saves images to Google

Homemade "Black Forest Labs FLUX.1 Diffusion Model Python Client"

Image generation and editing with Black Forest Labs' FLUX models (v1.1-pro, v1-kontext and v2-pro) in Azure AI Foundry via direct API calls and Entra ID auths.

This repository contains comprehensive documentation and analysis of **FLUX.1-Krea [dev]**, an advanced 12-billion parameter text-to-image model representing a unique collaboration between Black Forest Labs (BFL) and Krea AI.

A tool for creating creative images.

Générateurs d'assets pour Radio Cause Commune