Qwen/Qwen-Image-Layered
Image-Text-to-Image β’ 20B β’ Updated β’ 78.5k β’ 1.16k
AnisoraV3 (anime image to video generation) demo (14B)
New Ghibli EasyControl model is now released!!
High-fidelity 3D Geometry Generation from single view image
Generate any application by Vibe Coding it
Generate 3D video from input images
Generate music from a text description and optional melody
Start a FastAPI web server on port 7860
Chat with images using MiniGPT-4
Chat with a bilingual AI assistant