🔙 Go back to more models

AI Generator

PAN 2

Open-source AI world model
PAN 2 AI world model running locally in ComfyUI

PAN 2 is an open-source AI world model from the Institute of Foundation Models (IFM) at MBZUAI. You give it one photo and describe what happens next, and it predicts the result as a video, with the camera move you ask for. The code and weights are released under Apache 2.0. In Promptus you can run it with one click from a CosyFlow, locally or in Playground. Watch our full PAN 2 test.

PAN 2 specs

DeveloperIFM (Institute of Foundation Models), MBZUAI
ParametersAbout 29 billion
InputA start image plus scene, event and camera prompts (text to video is also supported)
OutputVideo at 1248×704, 24 fps, clips up to 20 seconds per IFM
LicenceApache 2.0 (code and weights)
ComfyUINative (core nodes); text encoder type set to pan2
Model filesDiffusion model 26.7 GB (int8), Qwen3.5 9B text encoder 9.7 GB (int8), Wan 2.2 VAE 1.4 GB

How PAN 2 works

Most image-to-video models animate a picture. A world model is trained to predict how a scene changes over time. PAN 2 was trained on structured captions, so it works best when you describe the scene, then what happens next (one action per line, in order), then the camera move. Our workflow builds that caption from three prompt boxes.

Our PAN 2 test

On an RTX 5090 Laptop GPU (24 GB VRAM) with 32 GB of RAM, a 5-second clip at 1248×704 took 14 min 37 s. VRAM peaked at 23.7 GB and system RAM at 31.5 GB.

How to run PAN 2 in Promptus

  1. Open the PAN 2 CosyFlow.
  2. From its menu choose Install Locally to download the models for you, or run it in Playground.
  3. Load your start image, fill in the scene, event and camera boxes, and press Run.

Prefer plain ComfyUI? Download the PAN 2 ComfyUI workflow or read our PAN 2 guide.

Sources: IFM's PAN 2 announcement and the PAN 2 model card. Speed and memory were measured by Promptus.

  • Previs and storyboards: see how a scene plays out from one frame before you shoot or animate it.
  • Short cinematic clips from a single photo, with a camera move you choose.
  • What-if shots: describe an action and watch the model predict the outcome.
  • Research and learning about world models, with commercial-friendly Apache 2.0 weights.
  • Steps: 50
  • CFG: 2.5
  • Shift: 9
  • Output: 1248×704 at 24 fps
  • Prompts: fill in scene, event (one action per line) and camera separately; a plain one-line prompt gives weaker results.
  • Hardware: plan for a 24 GB-class GPU, 32 GB+ RAM and about 38 GB of disk.
ai image generator

AI Generation Platform

Promptus AI is the easiest way to generate realistic photos, videos, 3D and ComfyUI workflows with artificial intelligence.

Our AI photo generator produces lifelike portraits, product images, and creative concepts in seconds, making it the perfect tool for creators and brands.

promptus ai video generator

Share your compute

Join our distributed GPU compute network. Help us make AI accessible, scalable
and secure for designer, developers and start-ups.

promptus ai video generator