LongCat Image Editing is the image editing version of Longcat-Image. It is an open-source image editing model that supports both Chinese and English. It has reached the advanced level of open-source models in terms of instruction following, image quality, and visual consistency, and has excellent precise editing and consistency preservation capabilities.

MultimodalTransformersMultiple Languages

Z-Image is an efficient basic image generation model with 6 billion parameters, specifically designed to address the efficiency and quality issues in the field of image generation. Its distilled version, Z-Image-Turbo, can reach or exceed the leading competitors with only 8 function evaluations. It can achieve sub-second inference latency on enterprise-level H800 GPUs and run on consumer-grade devices with 16G VRAM.

Computer VisionDiffusersMultiple Languages

Z-Image is a powerful and efficient image generation model with 6 billion parameters. It can effectively solve the problems in the fields of image generation in terms of efficiency, quality, and functional diversity, providing users with high-quality image generation and editing services.

Computer VisionDiffusersEnglish

SteadyDancer is a powerful animation framework based on the image-to-video paradigm, specifically designed to generate high-fidelity and temporally coherent human body animations. This framework effectively solves the identity drift problem in traditional methods through a robust first frame retention mechanism, performs excellently in visual quality and controllability, and significantly reduces the training resource requirements.

Computer VisionDiffusers

Qwen-Image-Edit-2509_clear is a fine-tuned version of the Qwen-Image-Edit-2509 model, specifically optimized for image generation quality. This model can generate clearer and more vivid images with higher contrast, richer colors, and more refined details.

Computer VisionGguf

UltraFlux is a diffusion transformer based on Flux, specifically designed for native 4K text-to-image generation. Through the collaborative design of data, architecture, and loss, it can maintain consistent image quality under various aspect ratios.

Computer VisionDiffusersEnglish

Hunyuan Video-1.5 is a lightweight and high-performance video generation model. With only 8.3 billion parameters, it can provide top-notch video quality, significantly lowering the usage threshold. It can run smoothly on consumer-grade GPUs, supporting text-to-video and image-to-video generation, enabling every developer and creator to use it easily.

MultimodalDiffusersMultiple Languages

This is an enhanced multimodal vision-language model based on the Qwen3-VL-8B-Thinking model. It is extended to 12B parameters through Brainstorm 20x technology and uses NEO Imatrix-enhanced GGUF quantization. The model has powerful image understanding, text generation, and multimodal reasoning capabilities, with significant improvements in visual perception, text quality, and creative scenarios.

MultimodalGgufMultiple Languages

This project is a quantized version of the text-to-image model Nepotism based on the Flux architecture, optimized using SVDQuant technology. It offers two quantization formats, INT4 and FP4, suitable for different generations of GPU hardware respectively, significantly reducing the model size and memory usage while maintaining image generation quality.

MultimodalDiffusersEnglish

This is the Nunchaku quantization (SVDQ) version of the UltraReal Fine-Tune text-to-image model based on Danrisi's Flux architecture. The model offers two quantization formats: INT4 for non-Blackwell architecture GPUs (before the 50 series) and NVFP4 for Blackwell architecture GPUs (50 series), aiming to reduce hardware requirements while maintaining image generation quality.

Computer VisionDiffusersEnglish

Qwen-Image-Edit-MeiTu is an improved version based on Qwen-Image-Edit. It is fine-tuned using the DiT architecture and focuses on enhancing visual consistency, aesthetic quality, and structural alignment capabilities in complex image editing.

Computer VisionDiffusersMultiple Languages

A quantized version of the text-to-image model based on Flux.1, using SVDQ quantization technology, offering two precisions, INT4 and FP4, suitable for users with different GPU configurations. It significantly reduces the model size and memory usage while maintaining image quality.

Computer VisionDiffusersEnglish

Based on Stable Diffusion XL, the UNet weights are fine-tuned using the Inversion-DPO method, combining direct preference optimization (DPO) technology and the inversion method to improve the quality and alignment of image generation in the diffusion model.

Computer VisionDiffusers

An SVDQ quantized version of the text-to-image generation model developed based on Flux.1, offering two quantization formats, INT4 and FP4, optimized for different GPU architectures. It significantly reduces VRAM usage and improves inference speed while maintaining image quality.

Computer VisionDiffusersEnglish

natalie_wan_2.2-lora is a LoRA model trained based on AI Toolkit by Ostris, specifically designed for text-to-video conversion tasks, which can effectively improve the quality and effect of image generation.

MultimodalDiffusers

Nova Anime XL is a text - to - image generation model based on the Stable Diffusion XL architecture, specifically designed to generate high - quality images in various styles such as anime, fantasy, and landscapes. It combines the advantages of multiple excellent base models and performs outstandingly in terms of details, characters, backgrounds, and color representation.

Computer VisionDiffusersEnglish

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

simpletuner-lora is a LoRA fine-tuning model based on PEFT, derived from stabilityai/stable-diffusion-3.5-large, specifically designed for text-to-image and image-to-image conversion tasks. This model has been trained for 162 epochs, featuring efficient inference capabilities and good image generation quality.

MultimodalDiffusers

NetaYume Lumina Image 2.0 is a text-to-image diffusion model that has been quantized in the GGUF format and can convert text descriptions into images. The model has been optimized to reduce memory usage and improve performance while maintaining generation quality.

MultimodalGgufEnglish

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