
lodestones/Chroma
Text-to-Image
β’
Updated
β’
469
Generate images from text prompts
Generate stable LEGO structures from text prompts.
Infinite-Length Film Generation
β»οΈ Upscale any video using several models
State-of-the-art VLM to solve multimodal reasoning problems
θͺε¨δΈΊεΎηζ·»ε εεΊη±³ι©¬θ΅ε ηε·₯ε ·γ
Generate video from image and prompt
HunyuanCustom, a multi-modal, conditional, and controllable
Object Detection on Images and Video
fast video generation from images & text