This model is a joke rating model fine-tuned on multilingual text based on FacebookAI/xlm-roberta-large. It is specifically designed to evaluate the quality and humor level of jokes. It achieved an accuracy of 0.4005 and a root mean square error of 5.0327 on the evaluation set.

Natural Language ProcessingTransformers

The MiMo Embodied Model (MiMo-Embodied) is a powerful cross-embodied vision-language model that has demonstrated excellent performance in both autonomous driving and embodied AI tasks. It is the first open-source vision-language model that combines these two key domains, significantly enhancing the understanding and reasoning abilities in dynamic physical environments.

MultimodalTransformers

NV-Reason-CXR-3B GGUF is a quantized version of the NVIDIA NV-Reason-CXR-3B vision-language model, optimized for edge device deployment. This is a model with 3 billion parameters, focusing on chest X-ray analysis. It has been converted to the GGUF format and quantized for efficient operation on mobile devices, desktops, and embedded systems.

MultimodalGgufEnglish

TRELLIS Text XL is a large-scale 3D generation model, which is the text-conditioned version of TRELLIS with an XL model size. This model is proposed based on the paper 'Structured 3D Latents for Scalable and Versatile 3D Generation' and can generate high-quality 3D content according to text descriptions.

This is the latest cutting-edge model in the field of accuracy, dedicated to achieving artificial grain intelligence, and has made significant progress with the assistance of the world's top grain planting teams. This model is based on the Qwen3-0.6B architecture and is fully fine-tuned locally using an RX 9070 XT graphics card and the unsloth tool.

Natural Language ProcessingSafetensorsEnglish

A statement detection model fine-tuned based on BERT-base-uncased, capable of efficiently determining whether a given sentence is a statement worth verifying, and has wide applications in fields such as insurance and fraud detection.

Natural Language ProcessingTransformers

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

DreamOmni2-GGUF is an image-to-image model that converts the xiabs/DreamOmni2-7.6B model to the GGUF format. It supports multimodal instruction editing and generation and follows the Apache-2.0 license.

MultimodalGguf

This is a LoRA adaptation weight based on the Stable Diffusion XL base model 1.0, specifically fine-tuned for a specific style and can be used to generate images with a specific artistic style.

Computer VisionDiffusers

xLSTM-7b-Instruct is an experimental fine-tuned version based on NX-AI/xLSTM-7b, specifically optimized for instruction-following tasks. This model adds support for chat templates and uses TRL for supervised fine-tuning training, aiming to provide a better conversational interaction experience.

Natural Language ProcessingTransformers

XL-Sat-IOR is a text-to-image generation model based on the Stable Diffusion and Stable Diffusion XL architectures. It can generate images with a high degree of realism, rich colors, movie-like texture, fine details, excellent lighting and shadow effects, and vivid facial expressions.

Computer VisionDiffusersEnglish

This is a text-to-image generation model based on Stable Diffusion and Stable Diffusion XL technologies. It is specifically optimized for portrait, texture, and skin performance, capable of generating realistic and natural images.

Computer VisionDiffusersEnglish

This is a text-to-image generation model based on Stable Diffusion XL, optimized specifically for Asian-style image generation, capable of generating image works with realism and aesthetic appeal.

Computer VisionDiffusersEnglish

A version fine-tuned based on google/medgemma-4b-it, specifically designed for binary breast X-ray image classification on the OMAMA 256×256 dataset. This model uses LoRA (Low-Rank Adaptation) for parameter-efficient adjustment and performs excellently in the breast cancer classification task, with the accuracy increasing from 12% of the base model to 95%.

MultimodalTransformersEnglish

ohwx2_wan-lora is a LoRA model based on text-to-video generation, trained using AI Toolkit, specifically designed for image generation tasks. It requires a specific trigger word 'ohwx girl' to activate the generation effect.

MultimodalDiffusers

This is a LoRA model trained based on AI Toolkit, specifically designed for the image-to-video conversion task. The model is trained based on the Qwen/Qwen-Image base model and uses the creativeml-openrail-m license.

MultimodalDiffusers

Illustrious-xl-early-release-v0 is a text-to-image generation model based on the Stable Diffusion XL architecture, specifically optimized for anime and 2D illustration styles, capable of generating high-quality image works based on text descriptions.

Computer VisionDiffusersEnglish

XTTS v2 GGUF is a memory-efficient text-to-speech system optimized for mobile devices. It uses a C++ inference engine to achieve ultra-low memory usage and fast loading.

Audio ProcessingGgufMultiple Languages

X-Codec-2.0-25TPS-24k is a speech codec model improved based on HKUSTAudio/xcodec2. It reduces the transactions per second from 50 to 25 and increases the output sampling rate to 24kHz, optimizing the processing efficiency while maintaining the voice quality.

Audio ProcessingTransformers

A quantized version based on Stable Diffusion XL Base 1.0, achieving 4-bit quantization through SVDQuant technology, significantly improving inference efficiency while maintaining high-quality image generation capabilities.

Computer VisionDiffusersEnglish