The classic browser UI for Stable Diffusion: text-to-image, inpainting, upscaling and thousands of community extensions.
All repositories
Voice, video, multimodalWan-Video
Wan2.1
Open video-generation models: turn text or an image into a clip. The 1.3B version fits in roughly 8 GB of VRAM.
Who it is for
People who want to generate video locally on a consumer GPU.
How to start
- Clone:
git clone https://github.com/Wan-Video/Wan2.1.gitandcd Wan2.1. - Install dependencies:
pip install -r requirements.txt. - Download weights:
pip install "huggingface_hub[cli]", thenhuggingface-cli download Wan-AI/Wan2.1-T2V-14B --local-dir ./Wan2.1-T2V-14B.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+194Sep 6 — Oct 5
Author's description
Wan: Open and Advanced Large-Scale Video Generative Models
More in «Voice, video, multimodal»
A node-based builder for diffusion pipelines: wire up image, video and audio generation visually. Runs locally and exposes API endpoints.
OpenAI's reference speech-recognition model: transcribes audio in dozens of languages, translates speech and detects the language.
Few-shot voice cloning: about a minute of recorded speech is enough to fine-tune a text-to-speech model. Ships a web UI for data prep and training.
Whisper rewritten in C/C++: runs fast on a plain CPU and on Macs with no Python or heavy dependencies. Easy to embed in apps.
A speech-synthesis model tuned for natural conversational dialogue: handles pauses, laughter and intonation. Good for voice assistants and dialogue voice-over.