Wan2.2 is a major upgrade version of the basic video model, focusing on integrating innovative technologies such as effective MoE architecture, efficient training strategies, and multimodal fusion into the video diffusion model, bringing more powerful and efficient solutions to the field of video generation.

MultimodalDiffusersMultiple Languages

Kimi Linear is a hybrid linear attention architecture that outperforms traditional full attention methods in various scenarios, including short and long contexts, as well as reinforcement learning extension mechanisms. It can effectively solve the problem of low efficiency of traditional attention mechanisms in long context tasks and bring more efficient solutions to fields such as natural language processing.

Natural Language ProcessingTransformers

Wenxin Edit 2509 Image Fusion LoRA is an image relighting LoRA model developed based on the Qwen-Image-Edit-2509 model. It can bring excellent light processing effects to images and achieve professional-level image relighting functions.

Computer VisionDiffusers

A LoRA model based on Qwen-Edit-2509, providing powerful image fusion and relighting functions, and bringing new visual effects to images.

Computer VisionDiffusers

SongBloom is a generative model focused on text-to-audio conversion. It can transform text into vivid audio content, bringing users a brand - new speech synthesis experience.

This is a LoRA model trained based on AI Toolkit by Ostris, specifically designed for text-to-video conversion, bringing a new experience to image generation. This model needs to be used in conjunction with the base model Wan2.2-T2V-A14B.

MultimodalDiffusers

animat3d_style_wan-lora is a LoRA model trained based on AI Toolkit by Ostris, specifically designed for text-to-video generation, which can bring unique 3D animation style effects to image generation. This model is fine-tuned based on the Wan2.2-T2V-A14B base model and supports use on multiple mainstream AI platforms.

Computer VisionDiffusers

This is a LoRA model trained based on the AI Toolkit by Ostris, specifically designed for image-to-video conversion, bringing dynamic effects to static image generation.

MultimodalDiffusers

NeuTTS Air is the world's first ultra-realistic, edge-side text-to-speech (TTS) language model with instant voice cloning capabilities. Built on a large language model backbone with 0.5B parameters, it brings natural voice, real-time performance, built-in security, and speaker cloning capabilities to local devices.

Audio ProcessingGguf

The monthly iteration version of the Tongyi Image Editing Model, which supports multi-image editing, improves the consistency of single-image editing, and natively supports ControlNet, bringing more powerful functions and better effects to image editing.

MultimodalDiffusersMultiple Languages

NeuTTS Air is the world's first ultra-realistic, device-side text-to-speech (TTS) language model with instant voice cloning capabilities. Built on a 0.5B large language model backbone network, it can bring natural voice, real-time performance, built-in security features, and speaker cloning capabilities to local devices.

Audio ProcessingSafetensors

This is a fine-tuned and quantized version of Tencent's SRPO model, which mainly improves the clarity of generated images and the model's compatibility. It provides 8-bit/4-bit quantization options, bringing users a better experience.

Computer VisionDiffusersEnglish

Gödel Prover V2 is an open-source language model series that has set a new benchmark in automated formal proof generation. It is built based on expert iteration and reinforcement learning, incorporating three key innovations, and has demonstrated excellent performance in multiple benchmark tests, bringing new breakthroughs to the field of theorem proving.

Natural Language ProcessingTransformers

Cthulhu-24B-v1 is a creative and uncensored pre-trained language model fusion that combines the advantages of multiple pre-trained language models to bring a new experience to text generation tasks.

Natural Language ProcessingTransformersEnglish

Chinda LLM 4B is a cutting-edge Thai model launched by iApp Technology, built on the Qwen3-4B architecture, bringing advanced thinking capabilities to the Thai AI ecosystem.

Natural Language ProcessingGgufMultiple Languages

Qwen3-8B is a large language model in the Qwen3 series. It has the characteristics of a causal language model and performs excellently in reasoning, multilingual support, agent capabilities, etc., bringing users a natural and smooth conversation experience.

Natural Language ProcessingTransformers

Qwen3-8B is the latest large language model in the Qwen series. It has a variety of advanced features, supports multiple languages, and performs excellently in reasoning, instruction following, etc., bringing users a more intelligent and natural interaction experience.

Natural Language ProcessingTransformers

apu_apustaja_cartoon is a text-to-image model that can generate relevant cartoon images based on specific trigger words, bringing new possibilities to image creation.

Computer VisionDiffusers

This is a text-to-image LoRA model that can generate high-quality images based on specific prompts, bringing more possibilities to image creation.

Computer VisionDiffusers

The Neon Sign LoRA model is based on the Flux.1 D architecture and is specifically trained for piped neon sign images. This model excels in generating text-related neon signs and can also generate icons and emojis, bringing a unique neon style effect to image generation.

Computer VisionDiffusers