VoxCPM is an innovative tokenizer-free end-to-end text-to-speech (TTS) system that overcomes the limitations of discrete tokenization by modeling speech in a continuous space. It has two core capabilities: context-aware speech generation and realistic zero-shot voice cloning. It can automatically adjust the prosody and style according to the text content and clone the speaker's timbre, accent, and emotion with just a short reference audio.

Audio ProcessingSafetensorsMultiple Languages

This project provides a quantized GGUF version of the Tencent HunyuanVideo-1.5-I2V-720p model, specifically designed for image-to-video and video generation tasks. The model supports converting static images into high-quality video content and offers multiple quantized versions to optimize performance.

MultimodalGguf

The first truly open-source and unrestricted anime video generation model, based on the Wan2.2-5B architecture, can run with only 6GB of video memory and can generate amazing anime animation content.

MultimodalDiffusers

A large language model with 12B parameters fine-tuned based on Qwen 3, capable of handling 256k ultra-long contexts. It is specifically optimized for long text generation tasks. This model combines the foundation of the VLTO 8B model, Brainstorm 20x tuning, and NEO Imatrix dataset quantization technology, enabling it to generate high-quality long text content.

Natural Language ProcessingGgufMultiple Languages

This is a statically quantized GGUF version of the Manoghn/voicecraft-mistral-7b model, based on the Mistral-7B architecture, specifically designed for content generation and text generation tasks. This version offers multiple quantization levels, ranging from 2.8GB to 14.6GB. Users can choose the appropriate version according to their hardware conditions and performance requirements.

Natural Language ProcessingTransformersEnglish

This is a text-to-video generation model that converts the hlwang06/HoloCine model to the GGUF format. It supports generating video content based on text descriptions and uses the Apache-2.0 license.

MultimodalGguf

This is a text generation model fine-tuned on an internal horror dataset based on the Gemma-3 model, specifically designed for generating horror-style content. The model is optimized through Unsloth and can generate horror content ranging from mild to intense, including long horror stories.

Natural Language ProcessingGgufMultiple Languages

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.

LAM-1 is the first complete version of the small language model in the lamina series, developed by Clemylia. This model focuses on creative content generation and is optimized to generate imaginative, poetic, and narrative answers rather than factual information.

Natural Language ProcessingTransformersFrench

LibreFLUX-ControlNet is a text-to-image generation model based on the ControlNet architecture, using LibreFLUX as the base Transformer model. This model is trained on the SA1B dataset and can generate high-quality image content based on text prompts and control images.

Computer VisionDiffusers

svizz is a text-to-image generation model based on LoRA technology. It uses LyliaEngine/Pony_Diffusion_V6_XL as the base model and can generate high-quality image content through specific trigger words.

Computer VisionDiffusers

This is a LoRA model trained based on AI Toolkit by Ostris, specifically designed for the text-to-video image generation task. Use the trigger word 'Lilly' to generate image content in a specific style.

MultimodalDiffusers

UIGENT-30B-Lora-200 is a large language model fine-tuned based on Qwen3-Coder-30B-A3B-Instruct. It is specifically optimized for text generation tasks and is particularly good at handling HTML-related content. It also has various text generation capabilities.

Natural Language ProcessingTransformers

Ovi is an advanced audio-video generation model that can simultaneously generate synchronized video and audio content based on text or text + image input. This model adopts a dual-backbone architecture and supports 5-second video generation, providing a powerful tool for multimedia creation.

MultimodalSafetensorsEnglish

OmniDimen-V1.1-4B-Emotion is an emotion recognition and emotion-aware text generation model fine-tuned based on Qwen3-4B-Instruct-2507. It is specifically designed to accurately identify the emotional tendency of text and generate matching emotional content, providing users with a more emotionally resonant interaction experience.

Natural Language ProcessingGgufMultiple Languages

CAST 0.7B is a speech-to-speech language model built on a 0.7B parameter Gemma3-style language model, capable of generating natural speech audio continuation content. This model relies on the CAST WavTokenizer for encoding/decoding operations and is specifically designed for speech generation tasks.

Audio ProcessingSafetensors

Wan2.2-S2V-14B is a Mixture of Experts (MoE) model designed for audio-driven cinema-level video generation. It can generate high-quality video content based on input audio, reference images, and text prompts, supports 480P and 720P resolutions, and features complex motion generation and cinema-level aesthetic effects.

MultimodalDiffusersSpanish

This is a LyCORIS adapter based on Qwen/Qwen-Image, specifically designed for text-to-image generation tasks. The model can generate corresponding images based on the input text description, and is particularly good at generating image content with graffiti style and mixed media effects.

MultimodalDiffusers

Seed-OSS-36B-Instruct is a large language model with 36 billion parameters developed by ByteDance. It is optimized based on the MLX framework and focuses on text generation tasks. This model supports both English and Chinese, and uses the Apache 2.0 open-source license. It has powerful instruction-following and content generation capabilities.

Natural Language ProcessingMlxMultiple Languages

Chroma is a high-quality text-to-image generation model that focuses on generating realistic image content. This model uses advanced diffusion technology and can generate high-quality visual content based on text descriptions, which is particularly suitable for image creation needs in local deployment environments.

Computer VisionGgufEnglish