A quantized version of the text-to-image generation model developed based on Flux.1, using SVDQ quantization technology, offering two quantization formats, INT4 and FP4, suitable for efficient image generation on different hardware platforms.

Computer VisionDiffusersEnglish

A quantized version of the text-to-image generation model developed based on Flux.1-Dev of J1B, optimized using SVDQuant technology, offering two quantization formats, INT4 and FP4, suitable for users with different GPU architectures.

Computer VisionDiffusersMultiple Languages

PixelWave is a text-to-image model developed based on Flux.1. It has been optimized through Nunchaku quantization (SVDQ), providing an efficient image generation solution for users with different GPU configurations.

Computer VisionDiffusersEnglish

kontext-dusk-3-lora is a LoRA image generation model trained based on the FLUX.1-Kontext-dev base model, specifically designed to generate images in the style of the twilight blue hour. This model is triggered by specific trigger words and supports the use of multiple mainstream AI image generation tools.

Computer VisionDiffusers

Outfit-Cut is an adapter for FLUX.1-Kontext-dev of black-forest-lab, specifically designed to accurately extract specified clothing items from images. This model has been trained on 200 pairs of images and can place the clothing on a clean, solid-color background, presenting it in a professional product photography style while preserving the original texture, color, shape, and details of the clothing.

Computer VisionDiffusers

FLUX.1 Wireframe [dev] LoRA is an improved version of FLUX.1-Layout-ControlNet. As a key component of SpatialGen, it can generate images based on text descriptions while following the structure of a given wireframe image. This model is suitable for the FLUX.1 [dev] framework and is specifically designed for indoor scene generation tasks.

MultimodalDiffusers

Flux.1-Dev SRPO LoRAs are a set of lightweight adaptation models for text-to-image conversion, extracted from multiple sources, supporting modular mixing and rapid experiments on different ranks.

Computer VisionDiffusers

poshanimals is a text-to-image generation model trained based on the FLUX.1-dev model. It is trained using AI Toolkit by Ostris and can generate image works with a specific style according to text descriptions.

Computer VisionDiffusers

SRPO is a human preference alignment method for diffusion models. Through Direct-Align technology and semantic relative preference optimization, it significantly improves the realism and aesthetic quality of the FLUX.1-dev model, and solves the problems of high computational cost in multi-step denoising and dependence on offline reward fine-tuning.

Computer VisionDiffusers

RUSKANIME2025 is a text-to-image generation model based on LoRA and Diffusers technologies, specifically designed to generate relevant anime-style images through specific trigger words. This model is built on the black-forest-labs/FLUX.1-dev base model and uses the diffusion LoRA template technology.

Computer VisionDiffusers

This is a text-to-image generation model based on LoRA and Diffusers technology. It uses the specific trigger word 'Put it here' to generate high-quality images. This model is built on the FLUX.1-Kontext-dev base model and supports adaptive light adjustment and 4K high-definition picture quality output.

Computer VisionDiffusers

Pola Photo (Flux Dev) is an image generation model based on Flux.1-dev, specifically designed to generate realistic images with the style of Polaroid instant photos. This model is trained on the Replicate platform using open-source materials and follows the CC non-commercial attribution license agreement.

Computer VisionDiffusers

FLUX.1-Layout-ControlNet is a key component of the SpatialGen framework and is a ControlNet model based on semantic image conditioning. It can generate 2D images according to text descriptions while strictly following the layout constraints of the input semantic image, mainly used for 3D indoor scene synthesis.

MultimodalDiffusers

Chroma1-HD is a text-to-image generation base model based on the FLUX.1-schnell architecture, with 8.9 billion parameters, and uses the Apache 2.0 open-source license. This model is specifically designed for fine-tuning, providing a powerful image generation foundation for developers and researchers, and supporting the creation of various specialized visual content.

Computer VisionDiffusers

FLUX.1 [dev] is a rectified flow transformer with 12 billion parameters, specifically designed for text-to-image generation. It excels in image generation quality, second only to FLUX.1 [pro], with excellent prompt following ability and an efficient training method, providing strong support for scientific research and creation.

MultimodalDiffusersEnglish

A LoRA fine-tuning model created based on the FLUX.1-Kontext-dev base model, specifically designed for generating glistening portrait images with an artistic style, supporting text-to-image and image-to-image generation tasks.

Computer VisionDiffusersMultiple Languages

This is a FLUX.1 Krea dev model quantized by the Nunchaku team using SVDQuant technology, specifically designed for text-to-image generation. While maintaining the ability to generate high-quality images, this model significantly improves inference efficiency and is suitable for non-commercial use.

Computer VisionDiffusersEnglish

The GGUF quantized version of Krea is a text-to-image generation model based on the FLUX.1 architecture. It optimizes the model size and inference efficiency through GGUF quantization technology and supports running in multiple ways such as via the diffusers library, ComfyUI, and gguf-connector.

MultimodalDiffusersEnglish

FLUX.1 Krea [dev] is a rectified flow transformer model with 12 billion parameters, specifically designed to generate high-quality images based on text descriptions. This model uses FP8 quantization technology and has the same characteristics as the original FLUX.1 [dev], but is optimized for improved performance. The model's output can be used for personal, scientific, and commercial purposes, but it must comply with the non-commercial license agreement.

Computer VisionDiffusers

FLUX.1 Krea [dev] is a rectified flow transformer with 12 billion parameters, capable of generating high-quality images based on text descriptions. This model focuses on aesthetic photography and excels in image quality and instruction following. It uses guided distillation for efficient training and opens its weights to promote scientific research and artistic creation.

MultimodalDiffusersEnglish