Uni-MoE 2.0-Omni is a fully open-source full-modal model launched by Lychee Technology. It adopts the full-modal 3D RoPE and dynamic-capacity mixture-of-experts architecture, significantly enhancing the language-centered multi-modal understanding, reasoning, and generation capabilities. This version integrates full-modal understanding as well as audio and image generation capabilities.

MultimodalTransformersMultiple 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.

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

MapAnything is an end-to-end trained Transformer model that can take multiple modalities as input and directly regress the decomposed metric 3D geometric structure of the scene. This model supports more than 12 different 3D reconstruction tasks, including multi-image SfM, multi-view stereo vision, and monocular metric depth estimation.

Computer VisionSafetensorsEnglish

FLUX.1-Layout-ControlNet is a key component of the SpatialGen framework and is a ControlNet model based on semantic image conditioning. It can generate 2D images according to text descriptions while strictly following the layout constraints of the input semantic image, mainly used for 3D indoor scene synthesis.

MultimodalDiffusers

STream3R is a scalable sequential 3D reconstruction model based on causal Transformer, which redefines point cloud map prediction as a decoder-only Transformer problem. It introduces a streaming processing framework, efficiently processes image sequences using causal attention, and can generalize well to various challenging scenarios, including dynamic scenes where traditional methods often fail.

Computer VisionSafetensors

ESM-2 is a protein language model optimized by NVIDIA based on TransformerEngine, which can predict the 3D structure of proteins from amino acid sequences. This model is trained with a masked language modeling objective and has faster training and inference speeds on NVIDIA GPUs.

Scientific ComputingTransformers

This is a LoRA model that can convert ordinary images into metallic-style images with a black background and a 3D perspective.

Computer VisionDiffusersMultiple Languages

AnySplat is an advanced 3D Gaussian Splat rendering model that can efficiently generate high-quality 3D scenes from images taken from different perspectives. This model has fast inference capabilities and good generalization performance, providing an innovative solution for 3D reconstruction and rendering.

Computer VisionSafetensors

TRELLIS is a large-scale 3D generation model based on image conditions, utilizing structured 3D latent variables to achieve scalable and versatile 3D generation.

The text-conditioned version of TRELLIS, utilizing an XL-scale large model, is a powerful 3D generation model.

InternVL3 - 78B - Instruct is an advanced multimodal large language model that performs excellently in multimodal perception, reasoning, and language processing. Through the native multimodal pre - training method, this model integrates visual and language learning into a unified training stage and demonstrates outstanding capabilities in multiple fields such as tool use, GUI agents, industrial image analysis, and 3D visual perception.

MultimodalTransformersOther

InternVL3-2B-Instruct is an advanced multimodal large language model. Compared with its predecessors, it has better multimodal perception and reasoning capabilities, and has expanded in aspects such as tool usage, GUI agents, industrial image analysis, and 3D visual perception. It adopts a native multimodal pre-training method, integrating language and visual learning into a single pre-training stage.

MultimodalTransformersOther

InternVL3-14B-Instruct is an advanced Multimodal Large Language Model (MLLM) that demonstrates exceptional multimodal perception and reasoning capabilities, supporting various tasks such as tool usage, GUI agents, industrial image analysis, and 3D visual perception.

MultimodalTransformersmultilingual

LGM is an integrated image-to-3D workflow incorporating multi-view diffusion models, capable of generating high-quality 3D content from a single image.

Computer VisionDiffusers

InternVL3-78B is an advanced multimodal large language model with excellent multimodal perception and reasoning capabilities. It performs outstandingly in fields such as tool use, GUI agents, industrial image analysis, and 3D visual perception, and also has very good overall text performance.

MultimodalTransformersOther

InternVL3-14B is an advanced multimodal large language model that significantly improves multimodal perception and reasoning capabilities on the basis of InternVL 2.5 and expands applications in areas such as tool use, GUI agents, industrial image analysis, and 3D visual perception.

MultimodalTransformersOther

The image-conditioned version of TRELLIS is a large-scale 3D generation model capable of generating 3D content from images.

TRELLIS is a large-scale text-conditioned 3D generation model that utilizes structured 3D latent variables for scalable and versatile 3D content generation.

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