Use the FLUX-Pro model as much as you want.
plug-and-play with visual concepts
Discussions about the Inference Providers feature on the Hub
High-fidelity 3D Geometry Generation from images
Generate text and speech responses from text, images, or audio input
Deepseek v3-0324 + Real Time Deep Research
Generate audio from text using a reference audio sample
Transform an image into a textured 3D model
Generate a talking-head video from an image and audio
Chat with images and videos using Qwen
Inspired by Iron Man movies.
Hunyuan T1ๆจกๅไฝ้ช
interactive demo for cube 3d model
Try Orpheus TTS here
Gemini 2.0 native image generation co-doodling
Large Animatable Human Model
Transform flat-lay shots into on-model photos
MultiImages-to-3D Generation
Fast Images-to-3D Generation within 1 Second
Generate edited images with prompts