An enhanced local port of finegrain-image-enhancer powered by Refiners (https://huggingface.co/spaces/finegrain/finegrain-image-enhancer), which was adapted from philz1337x's Clarity Upscaler (https://github.com/philz1337x/clarity-upscaler)
Super Optimized Gradio UI for AI video creation for GPU poor machines (6GB+ VRAM). Supports Wan 2.1/2.2, Qwen, Hunyuan Video, LTX Video and Flux. https://github.com/deepbeepmeep/Wan2GP
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
[NVIDIA, ROCM] One app to train them all. LORA training and Model finetuning for Z-Image, Qwen Image, FLUX.1, Flux.2 Dev and Klein, Chroma, SD 1.5 - 3.5, SDXL, Würstchen-v2, Stable Cascade, PixArt-Alpha, PixArt-Sigma, Sana, Hunyuan Video and inpainting models.
[AMD ONLY] All-in-one local AI video, image & music studio built on the WanGP pipeline (Wan 2.1/2.2, LTX-2.3, Qwen, Hunyuan Video, Flux). ROCm-powered. Supported on Windows and Linux for RDNA 2-4 dGPUs (RX 6000/7000/8000/9000) and gfx1150-53 APUs (Strix Point/Halo, Krackan Point/Halo). 6 GB+ VRAM recommended. For NVIDIA GPUs use the upstream Maestro app. Credits: the app itself is Maestro by Blizaine (github.com/Blizaine/Maestro) — this is just an AMD installer wrapper around it. The clone-at-install-time approach used to port it to AMD was pioneered by 6Morpheus6's wan2gp-amd (github.com/6Morpheus6/wan2gp-amd).
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Describe an image, get a 100% schema-valid Ideogram 4 JSON prompt — generated fully locally with an embedded llama.cpp (no Ollama or LM Studio required).
Local LoRA trainer for MiniMax H3, Flux2 Klein 9B & Krea 2 — trains against the exact models you deploy. Desktop GUI + headless CLI. NVIDIA only (RTX 30/40/50, driver 555+).
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
PinokioLangGraph — Agent-StateSync for SillyTavern. A Pinokio script that runs a FastAPI + LangGraph agent as middleware between SillyTavern and your LLMs.
Apple Silicon image studio — FLUX.2 (klein/dev), FLUX.1 (schnell/dev/Kontext/lite), HiDream, Shuttle, Qwen-Image. Powered by MLX/mflux.
[NVIDIA ONLY] The most efficient way to run FLUX (Optimized to run even on low memory machines, as low as 3GB VRAM with 512x512 resolution) https://github.com/lllyasviel/stable-diffusion-webui-forge
Automatically clip videos and generate captions for LoRA training using advanced vision models like Gemma-3, Qwen3-VL, and Qwen2-VL.
[NVIDIA ONLY] Advanced Web UI for CogVideo (text to video, image to video, video to video, extend video, etc) -- Generate videos with less than 10GB VRAM
[Runs fast on NVIDIA GPUs. Works on M1/M2/M3 Macs but slow] VideoCrafter is an open-source video generation and editing toolbox for crafting video content. It currently includes the Text2Video and Image2Video models https://github.com/AILab-CVC/VideoCrafter