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

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

Hunyuan 3D-2 is a tool that supports image-to-3D and text-to-3D conversion, providing a powerful solution for 3D content generation.

Computer VisionDiffusersMultiple Languages

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

The TRELLIS image-conditioned version is a large-scale 3D generation model capable of generating corresponding 3D models from input 2D images.

The conditional image version of TRELLIS, a large-scale 3D generation model capable of creating 3D content from 2D images.

TripoSR is a fast feed-forward 3D generation model developed collaboratively by Stability AI and Tripo AI, capable of rapidly generating 3D models from a single image.

TRELLIS is a large-scale 3D generation model capable of generating 3D content based on image conditions

VALL-3D-Blender-Mix is a text-to-image generation model based on Stable Diffusion XL, specializing in anime, semi-realistic, 3D, and MMD-style images, with a particular strength in generating girl characters.

Computer VisionDiffusersMultiple Languages

NVComposer is a generative multi-view novel view synthesis model that requires no explicit external alignment, achieving high-quality 3D view generation through image-pose dual-stream diffusion and geometry-aware feature alignment.

Computer VisionDiffusersEnglish

TRELLIS Image Large is an image-conditioned version of the large-scale 3D generation model TRELLIS, capable of generating 3D content based on input images.

CraftsMan is a high-fidelity mesh generation system based on native 3D generation and interactive geometry optimization, capable of generating high-quality 3D mesh models from a single image.

Tencent Hunyuan3D-1.0 is a unified framework supporting text-to-3D and image-to-3D generation, achieving efficient and rapid 3D asset creation through a two-stage approach.

Computer VisionDiffusersMultiple Languages

A 3D rendering text-to-image model developed based on the FLUX framework, supporting high-quality 3D-style image generation through LoRA fine-tuning

Computer VisionDiffusersEnglish

A 3D animation-style text-to-image generation model based on Stable Diffusion technology, supporting Disney and anime-style 3D image generation.

Computer VisionGgufEnglish

3DTopia-XL is a high-quality 3D asset generation model based on the diffusion transformer (DiT) and PrimX representation, capable of quickly generating 3D PBR assets from text or image inputs.

An AI-based G-code generation model capable of generating G-code instructions for controlling plotters or 3D printers from images.

Natural Language ProcessingTransformersMultiple Languages

MeshAnything is an artist-grade mesh generation model based on autoregressive Transformers, capable of converting images or point clouds into high-quality 3D mesh models.

This is a version of the ImageDream model ported to diffusers for image-prompted multi-view 3D generation.

Computer VisionDiffusers