aiminute. ← All AI news
New Models AI Minute Newsroom 2026-10-04

Nvidia posted a new multimodal model and told nobody about it.

Nvidia posted a new multimodal model and told nobody about it.

A repository called PixelUMM appeared on Hugging Face on 1 October with a 15.2-billion-parameter checkpoint. Nvidia published no paper and no announcement, and the files are raw training shards nobody can load. The card says the model reads and generates both images and video, and is built on Alibaba's Qwen3-8B.

Why it mattersNvidia built this on a Chinese open base model, which shows how far those weights travel. Downloads still sit at zero, so treat it as a lab artefact rather than a product.
#Video#Image Generation

✓ Verified · 2 sources

WhatsApp X Telegram
Read in the app — free, in 9 languages

Related stories

Kuaishou's new Kling image model generates pictures in native 8K.
2026-11-19
Canva adds a switch that turns off most of its generative AI.
2026-11-19
Google opens its Genie 4 world generator to top-tier subscribers.
2026-11-19
Google's mid-tier Gemini 4 Neon edges past its own flagship in tests.
2026-11-19
Microsoft unveils its own coding model to undercut rivals on cost.
2026-11-18