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 • 623k • • 5.43k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • 12B • Updated • 395k • • 2.88k -
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • 14B • Updated • 137k • • 161 -
openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 3.79M • • 6.59k