Ava
Talk face to face with LFM3-Omni, running in your browser
Talk face to face with LFM3-Omni, running in your browser
Interactive Three.js 3D scenes from a prompt
Realistic Air speech and voice cloning with Audio8 0.6B
22 MB vision model - description, boxes, masks, OCR, forms
Text-to-image and image editing, based on MiniMax-H3
Two live CUGA agents, with and without policies
Generate 3D human motion from a video
Instant semantic search over pixel art, in your browser
A hands-on guide to training Mixture-of-Experts models
Which coding-agent harness should you use for your model?
generate a video from an image with a text prompt
Generate a video animation from a single image and prompt
Text-to-image and image editing, based on MiniMax-H3
Text-to-image and multi-image editing in 6 steps
Head swap with the BFS LoRA on Qwen-Image-2.1 (+turbo)
One image to a 3D object (Gaussian splats)
generate a video from an image with a text prompt with text
Generate explicit videos from your images
Talk face to face with LFM3-Omni, running in your browser
Instant semantic search over pixel art, in your browser
Edit images with Qwen and enhance with FLUX.2 Klein
Uncensored Qwen 2.1 with All-In-One LoRAs
Generate 3D human motion from a video
ltx 2.3 improved image-to-video with 10eros & native audio
Benchmarks and news on various repros of TypeSafe's Jev
Video generation with a synchronized soundtrack
Interactive Three.js 3D scenes from a prompt
YouTube to text transcript preview with timestamps.
Demo of the Collection of Qwen Image Edit LoRAs
text to video, image to video, video extend
Real-time t2i & editing with a Qwen-Image-2.1 2-step LoRA
Uncensored Qwen-Image-2.1 generate + edit