whatmodel.sh / image / ChronoEdit-14B
ChronoEdit-14B
↗ share
+ contribute
ChronoEdit-14B is an open-weights image model from NVIDIA, released October 2025. Its published size is 14B parameters. Licence: nvidia-open-model.
Catalogue identity notes
nvidia/ChronoEdit-14B (also published as nvidia/ChronoEdit-14B-Diffusers, same weights; card at revision 26b33e0: ~1.4e10 parameters, released on Hugging Face 2025-10-29, governed by the NVIDIA Open Model License). The optional 8-step distillation LoRA is a separate add-on and is not implied. No local command recorded.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of ChronoEdit-14B, out of 197 with a score, then more from NVIDIA.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 128 |  UniPic2-SD3.5M-Kontext-2B | 44±6 | comparison only | ||
| 129 |  UNO | 43±4 | local | ||
| 130 | ChronoEdit-14B | 43±3 | local | ||
| 131 |  Lumina-Image 2.0 | 43±4 | api $0.075/image +local | ||
| 132 |  BLIP3o-NEXT-GRPO-Text-3B | 42±3 | comparison only | ||
| more from NVIDIA | |||||
| 35 | Cosmos3-Super-Text2Image | 63±2 | local | ||
$ what it's good at
image to image / editing▁▁·▃▃▃█▃▃▄▁▁ #53 of 62 * · 95% of its score · 1 test
Beats FLUX1.1 [pro], UNO here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Edit-Compass (EN, overall) | 37.0% ✎ | ▃▃▂·▃▆▂█·▃·▃ beats 6/20 | 95% |
$ where to run it
Other ways to run it
- Run it as published · needs ~34 GB, NVIDIA only · from github.com/nv-tlabs
git clone https://github.com/nv-tlabs/ChronoEdit && cd ChronoEdit && conda env create -f environment.yml -n chronoedit_mini && conda activate chronoedit_mini && pip install torch==2.7.1 torchvision==0.22.1 && pip install -r requirements_minimal.txt && hf download nvidia/ChronoEdit-14B-Diffusers --local-dir checkpoints/ChronoEdit-14B-Diffusers && PYTHONPATH=$(pwd) python scripts/run_inference_diffusers.py --input assets/images/input_2.png --offload_model --prompt "Add a sunglasses to the cat's face" --output output.mp4 --model-path ./checkpoints/ChronoEdit-14B-Diffusers
Official weights and documentation: huggingface.co/nvidia ↗
$ how the score was worked out · Edit-Compass & EditReward-Com… 95%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling | 1 | 95% |
| prior · pull toward the middle | 5% | |
| weighted average | = 43.1 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json