Everything in the catalog

Generates lip-synced or audio-reactive video from an image and an audio track.

Generate talking video avatars in a podcast or TikTok style using the OmniAvatar model.

Paraphrases text to make it read more naturally.

FaceFlux: Instant CPU-Only Face Swap—No GAN Needed

SSI article and live Atlas Quick presets

Control your robot from anywhere and see what it sees.

Extracts text and images from PDFs or images with the Mistral OCR API; needs your Mistral key.

Upload PDFs, build a retrieval index and ask questions about them with a hosted language model.

Swaps faces between images using a Flux.2 Klein 9B LoRA.

The best open model for DNA understanding

Mirror of paperswithcode.co served as a Hugging Face Space.

Repairs scratched photos and upscales them.

Generate MIDI music using RWKV v4!

Creates images from text prompts with SDXL and SD 1.5 models.

Whisper speech recognition running on the Ratchet WebGPU runtime inside the browser.

Edits images with AI based on your instructions.

Generates 3D models from a text description or an image.

Generates embeddings with EmbeddingGemma 2 on WebGPU directly in the browser.

Co-Speech 3D Gesture Generation (CVPR 2024)

From an idea to a trained 4B, with the dead ends left in

A third-party component library based on Gradio.

NEW: LoRA size guard, CPU downloads & AI scene planning

Video generation app that creates actor-style character clips using the Ovi model.

Scans a repository for bugs using GLM models.