ankanmbz commited on
Commit
02aea7d
·
verified ·
1 Parent(s): 994fd87

Add model card

Browse files
Files changed (1) hide show
  1. README.md +59 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: image-to-video
3
+ library_name: diffusers
4
+ language:
5
+ - en
6
+ tags:
7
+ - world-model
8
+ - video-generation
9
+ - image-to-video
10
+ ---
11
+
12
+ <div align="center">
13
+
14
+ <img src="https://mbzuai-oryx.github.io/WorldGuide/assets/worldguide-logo.png" alt="WorldGuide" width="120"/>
15
+
16
+ # WorldGuide: Goal-Directed Video World Model for Procedural Task Execution
17
+
18
+ [Ankan Deria](https://ankan8145.github.io), [Komal Kumar](https://komalkumar.org), [Hisham Cholakkal](https://hishamcholakkal.com), [Fahad Shahbaz Khan](https://sites.google.com/view/fahadkhans), [Salman Khan](https://salman-h-khan.github.io)
19
+
20
+ **Mohamed bin Zayed University of Artificial Intelligence**
21
+
22
+ [![Project Page](https://img.shields.io/badge/Project-Page-2ea44f?logo=googlechrome&logoColor=white)](https://mbzuai-oryx.github.io/WorldGuide/)
23
+ [![GitHub](https://img.shields.io/badge/GitHub-Code-181717?logo=github&logoColor=white)](https://github.com/mbzuai-oryx/WorldGuide)
24
+
25
+ </div>
26
+
27
+ Official checkpoints for **WorldGuide**. Method details, results and training code are on the [project page](https://mbzuai-oryx.github.io/WorldGuide/) and on [GitHub](https://github.com/mbzuai-oryx/WorldGuide).
28
+
29
+ ## Checkpoints
30
+
31
+ ```text
32
+ WorldGuide-Ckpt/
33
+ ├── transformer/ # WorldGuide Video DiT → --action_ckpt
34
+ └── text_encoder/llm/ # WorldGuide ContextPlanner → --planner_model_path
35
+ ```
36
+
37
+ ## Usage
38
+
39
+ ```bash
40
+ git clone https://github.com/mbzuai-oryx/WorldGuide.git
41
+ cd WorldGuide
42
+ pip install -r requirements.txt
43
+
44
+ # Download this repository and all other required components into ./ckpts
45
+ python download_models.py --hf_token <your_hf_token>
46
+
47
+ # Run closed-loop inference
48
+ bash scripts/inference/run_v5_qwen_closed_loop_memory.sh
49
+ ```
50
+
51
+ ## Citation
52
+
53
+ ```bibtex
54
+ @misc{worldguide,
55
+ title = {WorldGuide: Goal-Directed Video World Model for Procedural Task Execution},
56
+ author = {Deria, Ankan and Kumar, Komal and Cholakkal, Hisham and Khan, Fahad Shahbaz and Khan, Salman},
57
+ year = {2026}
58
+ }
59
+ ```