WanGP adds LongCat Avatar: distilled lipsync video model for low-VRAM machines
cocktailpeanut · x · 2026-09-16
Dev cocktailpeanut noticed WanGP now supports LongCat Avatar 1.5 Distilled 13.6B, another lipsync video generation model. Wan2GP is an optimized Gradio UI for AI video creation on GPUs with as little as 6GB VRAM, also supporting Wan 2.1/2.2, Qwen, Hunyuan Video, LTX Video and Flux.
Related event: WanGP v13 Hits Pinokio: Local Video and Song Generation on Low-VRAM GPUs(5 posts)→
More from Multimodal
- Sora's Diffusion Transformer explained by hand in 14 steps: prompts enter only as scale and shift — ProfTomYeh · 2026-09-16
- ElevenLabs in one week: UMusic deal, Music v2.5, MCP multimodal, $1M AI SDR — lukeharries · 2026-09-16
- YuE2 Studio: A Local Web UI Bundling Music Generation and LoRA Training for Open-Source YuE2 — Cheap_Credit_3957 · 2026-09-16
- PhysStream Brings Physics-Grounded Mid-Generation Control to Streaming Video — Chuhao Chen · 2026-09-16
- YuE2 Open-Source Music Model Delivers 'Suno at Home', Best at 128 Steps — alisitskii · 2026-09-16
- Full-Song Lip-Synced MV with MiniMax H3 at 3 Steps: Method and Benchmarks — Disastrous_Page_301 · 2026-09-16