Wan2.1 Fast
Generate a video from an image with a prompt
Generate a video from an image with a prompt
Demo of Normalized Attention Guidance for FLUX.1-dev
Demo of Normalized Attention Guidance for 4 steps Wan2.1
Enhance images using sliders and AI
Consistency generation of portrait and subject
Unified MLLM with Text-Aligned Representations
Generate audio for a video using captions and descriptions
Extreme Super-Resolution via Scale Autoregression
Swap faces in videos
Generate music tracks and mix them into a full piece
In-browser text-to-music w/ Transformers.js!
Generate music from text descriptions
Generate music from text prompts
A Step Towards Music Generation Foundation Model
Generate music from text descriptions and optional melodies
Blazingly Fast and Embarrassingly Simple Song Generation
Generate videos from text prompts and optional images
Real-Time Image Generation with SDXL Lightning
Create videos with FFMPEG + Qwen2.5-Coder
Swap faces in images using a source image