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

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

A technical multiple-choice question generation model fine-tuned based on T5-base, specifically designed to generate relevant questions according to technical context and correct answers, suitable for the creation of educational content and assessments.

Natural Language ProcessingSafetensorsMultiple Languages

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

Nous-V1 8B is an 8-billion parameter language model developed by Apexion AI, built on the Qwen3-8B architecture. This model is designed for various natural language processing tasks and performs excellently in areas such as conversational AI, knowledge reasoning, code generation, and content creation. It strikes a good balance between model capabilities and actual deployment efficiency.

Natural Language ProcessingTransformersMultiple Languages

TRELLIS is a large-scale 3D generation model that achieves scalable and versatile 3D content creation through structured 3D latent variables.

This is a text classifier based on the ModernBERT-large architecture, specifically designed to identify and filter rejection expressions and other non-answer content in the fields of creative writing and role-playing, providing precise text screening functions for related creations and interactions.

Natural Language ProcessingTransformersEnglish

A model based on ModernBERT-base for predicting the reasoning complexity level (0-4) of text, suitable for educational content filtering and reasoning dataset creation.

Natural Language ProcessingTransformersEnglish

ZenCtrl is an intelligent agent that automates personalized visual content creation workflows, capable of performing various design tasks and training custom models.

An anime-style adapter based on Tencent's Hunyuan Video model, providing high-quality text-to-video generation capabilities, specifically optimized for anime-style content creation.

MultimodalGgufEnglish

A Gemma2 model optimized for novel and story creation, fine-tuned by integrating multiple top-notch story creation models, with more rich, delicate, and in-depth content generation capabilities.

Natural Language ProcessingGgufEnglish

A 70B-parameter large language model trained based on Llama 3.3 Instruct, specializing in dialogue generation and creative content creation

Natural Language ProcessingTransformers

The latest background removal model developed by BRIA AI, capable of effectively separating foreground and background in various images, suitable for large-scale commercial content creation scenarios.

Computer VisionTransformers

This is a large language model with 7.14B parameters based on the Llama 3.2 architecture, specifically designed for activities such as writing, fictional story creation, and storytelling. The model is optimized using the Brainstorm 40x method developed by David_AU and performs excellently in prose output, capable of generating text content with rich details and full emotions.

Natural Language ProcessingGgufEnglish

This is a Mistral Nemo large language model with a maximum context length of over 128k, optimized for writing and fictional creation. It is fused from three high-performance 'Gutenburg' models, possessing excellent storytelling ability and long-form content coherence, and is particularly good at prose creation and detail description.

Natural Language ProcessingGgufEnglish

Meta Llama 3.1 8B Instruct is a large language model optimized for instruction fine-tuning based on the Llama 3 architecture, with 8 billion parameters. It is specifically optimized for dialogue and instruction following tasks. This model performs excellently in various natural language processing tasks and supports functions such as multi-round dialogue, content creation, and code generation.

Natural Language ProcessingTransformers

LGM is a high-resolution 3D content creation pipeline integrating multi-view diffusion models, specifically designed for 3D machine learning courses.

Computer VisionDiffusers

LGM is a large multi-view Gaussian model for high-resolution 3D content creation, capable of generating 3D content from a single image.

Computer VisionDiffusers

This model can generate high-quality images based on input text descriptions, suitable for various scenarios such as creative design and content creation.

MultimodalDiffusers

A 13B-parameter large language model based on the Llama 2 architecture, specializing in story creation and narration, excelling at generating coherent and creative story content.

Natural Language ProcessingTransformersEnglish