Spaces:

hugging-apps
/

worldguide

Running on Zero

App Files Files Community

worldguide / README.md

multimodalart HF Staff

Trim gray placeholder frame in displayed clips; measured GPU duration; 20 steps default

9b9d87c verified 10 days ago

preview code

Raw History Blame Contribute Delete

1.7 kB

---
title: WorldGuide
emoji: 🧭
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 6.30.0
app_file: app.py
python_version: "3.10"
short_description: Goal-directed video world model, step by step
startup_duration_timeout: 1h
---
# WorldGuide

Interactive closed-loop demo of [WorldGuide: Goal-Directed Video World Model for Procedural Task Execution](https://huggingface.co/papers/2610.12459)
([code](https://github.com/mbzuai-oryx/WorldGuide), [weights](https://huggingface.co/ankanmbz/WorldGuide-Ckpt)).

Each press of the button runs one closed-loop step: the ContextPlanner (fine-tuned Qwen2.5-VL-7B) predicts the next atomic
action from the latest observation, and the WorldGuide video DiT (HunyuanVideo-1.5 480p I2V based, mode-2 step memory over the
last 2 steps) renders it as a 45-frame clip. Settings follow the authors' `run_v5_qwen_closed_loop_memory.sh`
(45 frames, CFG 7.5, shift 5, seed 3208, step-1 memory from a 1-second environment preview). The default is 20
denoising steps instead of the authors' 30 to keep each ZeroGPU call around 3 minutes; set 30 under Advanced settings.

## Example image credits

- `examples/seafood_pancake_ingredients.jpg` — "Korean pancake-Ingredients for Haemul pajeon" by draq (Flickr), via Wikimedia Commons, [CC BY 2.0](https://creativecommons.org/licenses/by/2.0) (cropped/resized).
- `examples/lego_bricks_desk.jpg` — "Lego messy desk" by Pascal from Heidelberg, Germany, via Wikimedia Commons, [CC BY 2.0](https://creativecommons.org/licenses/by/2.0) (cropped/resized).
- `examples/strawberries_cutting_board.jpg` — from [linoyts/repo-to-space-example-inputs](https://huggingface.co/datasets/linoyts/repo-to-space-example-inputs) (CC0).

	---
	title: WorldGuide
	emoji: 🧭
	colorFrom: green
	colorTo: blue
	sdk: gradio
	sdk_version: 6.30.0
	app_file: app.py
	python_version: "3.10"
	short_description: Goal-directed video world model, step by step
	startup_duration_timeout: 1h
	---

	# WorldGuide

	Interactive closed-loop demo of [WorldGuide: Goal-Directed Video World Model for Procedural Task Execution](https://huggingface.co/papers/2610.12459)
	([code](https://github.com/mbzuai-oryx/WorldGuide), [weights](https://huggingface.co/ankanmbz/WorldGuide-Ckpt)).

	Each press of the button runs one closed-loop step: the ContextPlanner (fine-tuned Qwen2.5-VL-7B) predicts the next atomic
	action from the latest observation, and the WorldGuide video DiT (HunyuanVideo-1.5 480p I2V based, mode-2 step memory over the
	last 2 steps) renders it as a 45-frame clip. Settings follow the authors' `run_v5_qwen_closed_loop_memory.sh`
	(45 frames, CFG 7.5, shift 5, seed 3208, step-1 memory from a 1-second environment preview). The default is 20
	denoising steps instead of the authors' 30 to keep each ZeroGPU call around 3 minutes; set 30 under Advanced settings.

	## Example image credits

	- `examples/seafood_pancake_ingredients.jpg` — "Korean pancake-Ingredients for Haemul pajeon" by draq (Flickr), via Wikimedia Commons, [CC BY 2.0](https://creativecommons.org/licenses/by/2.0) (cropped/resized).
	- `examples/lego_bricks_desk.jpg` — "Lego messy desk" by Pascal from Heidelberg, Germany, via Wikimedia Commons, [CC BY 2.0](https://creativecommons.org/licenses/by/2.0) (cropped/resized).
	- `examples/strawberries_cutting_board.jpg` — from [linoyts/repo-to-space-example-inputs](https://huggingface.co/datasets/linoyts/repo-to-space-example-inputs) (CC0).