TRELLIS
Scalable and Versatile 3D Generation from images
Scalable and Versatile 3D Generation from images
Note SOTA image-to-3D demo by Tsinghua & Microsoft Asia
Interact with a multimodal chatbot that analyzes images and text
Note InternVL2.5 by OpenGVLab
QwQ-32B-Preview
Huggingface space for JanusFlow-1.3B
Note MLLM By DeepSeek JanusFlow - a powerful framework that unifies image understanding and generation in a single model.
Generate code for applications
Note Code model by Alibaba Qwen team.
Generate and edit images using text instructions
Note Image model by the Bytedance Doubao team. It's an AI-powered image editing tool that allows you to edit images using simple text commands.
An end-to-end (e2e) Voice Language Model by Fish Audio.
Note Audio model By @Fishaudio Fish Agent v0.1 3B - New Speech to Speech model
Hunyuan-Large樑εδ½ιͺ
Note MoE by Tencent Hunyuan team. It's an open MoE model with 52B-parameter!
3D/4D Scenes from a Single Image w/ Controllable Video Diff
Note Video model by HKUST & Tsinghua A framework designed to generate photorealistic 3D and 4D scenes from just a single image with video diffusion
Image generator/identifier/reposer
Note Image model by BAAI It's a unified image generation model that can generate a wide range of images from multi-modal prompts.