Hunyuan3D-2.0
Text-to-3D and Image-to-3D Generation
Text-to-3D and Image-to-3D Generation
Easily expand image boundaries
Describe images, videos, and audio
edit images with Kontext and LoRAs
Add objects to images using prompts
Generate high-quality images from text prompts
Generate captions for images based on various styles and formats
Unified MLLM with Text-Aligned Representations
Upscale an image to higher resolution
Generate captions for images in various styles
Generate audio from text using a reference audio sample
Generate realistic dialogue from a script, using Dia!
Separate audio into stems using various models
Kontext multi image composition on FLUX[dev]
Online demo for XVerse
260+ impressive lora's for flux.1
Clarity AI Upscaler Reproduction
Create images from text descriptions
A Step Towards Music Generation Foundation Model
Monocular metric-scale geometry estimation
Translate text between 200 languages
Highlight moving points in a video
Convert vocals to match reference audio
Spanish finetune for the original F5 model.