huggingface-diffusers

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

Inpaint Anything extension performs stable diffusion inpainting on a browser UI using masks from Segment Anything.

Inpaint Anything performs stable diffusion inpainting on a browser UI using masks from Segment Anything.

[CVPR'25-Demo] Official repository of "TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models".

Dreambooth implementation based on Stable Diffusion with minimal code.

🤗 Unofficial huggingface/diffusers-based implementation of the paper "Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis".

A simple web application that lets you replace any part of an image with an image generated based on your description.

FireRed-Image-Edit-1.0-Fast is a high-performance, AI-driven image editing application that utilizes advanced diffusers and the QIE+ Pipeline for precise, prompt-based image modifications.

Quantized stable-diffusion cutting down memory 75%, testing in streamlit, deploying in container

Easily create your own AI avatar images!

Toolchain for creating custom datasets and training Stable Diffusion (1.x, 2.x, XL) models and LoRAs

Collection of OSS models that are containerized into a serving container

Experimental demonstration for the Qwen/Qwen-Image-Edit-2511 model with lazy-loaded LoRA adapters supporting multi-image input editing. Users can upload one or more images (gallery format) and apply advanced edits such as pose transfer, anime conversion, or camera angle changes via natural language prompts. Features integrated Rerun SDK.

QIE-Object-Remover-Bbox is an advanced, AI-powered image editing application specifically designed to perform precise object removal and background inpainting based on user-defined bounding box coordinates.

[ICML 2026] MAMBO-G: A training-free, magnitude-aware adaptive guidance framework for accelerating Classifier-Free Guidance (CFG). Dynamically mitigates early-step overshoot in flow-matching models (SD3.5, Qwen-Image, Wan2.1) to achieve 3x-4x speedup with high visual fidelity. Integrated into Hugging Face Diffusers.

TRELLIS.2-Text-to-3D is an end-to-end Text-to-3D and Image-to-3D generation app that enables users to create high-quality 3D GLB assets either by generating an image from a text prompt or by uploading an existing image, powered by Z-Image-Turbo and the TRELLIS.2 multi-stage pipeline.

Flux.2-4B-Encoder-Comparator is an experimental, dual-pipeline application designed to perform direct, side-by-side visual evaluations of the FLUX.2-klein-4B model using two different Variational Autoencoders (VAEs).

A Gradio-based demonstration for the Tongyi-MAI/Z-Image-Turbo diffusion pipeline, enhanced with a curated collection of LoRAs (Low-Rank Adaptations) for style transfer and creative image generation. Users can select from pre-listed LoRAs or add custom ones from Hugging Face repositories.

Qwen-Image-Edit-Object-Manipulator is an advanced, high-performance image manipulation workspace built on top of the Qwen/Qwen-Image-Edit-2511 base pipeline and enhanced by a custom optimized transformer.

Experimental Stable Diffusion XL Webui