nv-tlabs/ChronoEdit

[ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

45
/ 100
Emerging

Frames image editing as a video generation task, using input and edited images as start/end frames to leverage pretrained video diffusion models for temporal consistency. Introduces a temporal reasoning stage with reasoning tokens to ensure physically plausible edits and visualize intermediate editing trajectories. Integrates with Hugging Face Diffusers pipeline and supports LoRA fine-tuning through DiffSynth-Studio, with specialized variants for upscaling and inpainting tasks.

679 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 14 / 25

How are scores calculated?

Stars

679

Forks

41

Language

Python

License

Apache-2.0

Last pushed

Nov 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nv-tlabs/ChronoEdit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.