YangLing0818/EditWorld
[ACM Multimedia 2025 Datasets Track] EditWorld: Simulating World Dynamics for Instruction-Following Image Editing
This project helps researchers and developers working on advanced image and video editing by providing a dataset and framework for 'world-instructed' editing. You input existing images or video frames and a natural language instruction that describes a change in a real-world scenario. The output is a new image or video frame reflecting that instructed change. This is ideal for those developing AI models that understand and simulate complex real-world dynamics in visual content.
140 stars. No commits in the last 6 months.
Use this if you are a researcher or developer focused on building or evaluating AI models that can edit images and videos based on instructions grounded in complex real-world situations, rather than simple object manipulations.
Not ideal if you are looking for an end-user tool for casual image editing or a simple API to perform basic photo retouching.
Stars
140
Forks
6
Language
Python
License
—
Category
Last pushed
Aug 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/YangLing0818/EditWorld"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zai-org/CogVideo
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
zhaorw02/DeepMesh
[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
YangLing0818/RPG-DiffusionMaster
[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with...
thu-nics/FrameFusion
[ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token...
Yushi-Hu/tifa
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering