29B world model PAN 2 lands in Hugging Face Diffusers with t2v and i2v workflows
rohanpaul_ai · x · 2026-11-11
PAN 2 is a foundation world model that simulates how a scene evolves under a time-grounded plan of actions and camera movements. Its 29B generative simulator is a dual-stream multimodal diffusion transformer (the reasoning backbone that writes its prompts is not included). It's now integrated into Hugging Face Diffusers as Modular Diffusers blocks, supporting two workflows: t2v (prompt to video) and i2v (image + prompt to video). Sample code shows loading IFM/PAN2 via ModularPipeline in bfloat16 on CUDA and exporting with exporttovideo.
Related event: IFM Open-Sources PAN 2, a 29B-Parameter Video World Model(2 posts)→
More from Multimodal
- Japanese user's Fable 5.2 showcase video goes viral across languages — FinanceYF5 · 2026-11-11
- One-sentence prompt to Fable 5.2 yields jaw-dropping self-showcase video — FinanceYF5 · 2026-11-11
- AI-made music video "Slopcore, Encore" enters Claudia contest via Claude skill + Fable 5.2 — AIandDesign · 2026-11-11
- TRIAD benchmark: no multimodal retrieval system leads across its six subsets — _reachsumit · 2026-11-11
- Vision tokens far denser than text: paper traces VLM modality gap to early-layer processing — _reachsumit · 2026-11-11
- Fable 5.2 one-prompt short film "936": "make a video that will deeply change my life" — yuwen_lu_ · 2026-11-11