Popular image, video, speech, and audio models you can run via Replicate using Hugging Face Inference Providers.
-
Tongyi-MAI/Z-Image-Turbo
Text-to-Image • 6B • Updated • 730k • • 5.52k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 336k • • 2.92k -
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • 14B • Updated • 178k • • 163 -
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 3.57M • • 6.7k