direct-img/AuroraIMG-6M
1
0
Fork 0
mirror of https://github.com/direct-img/AuroraIMG-6M.git synced 2026-10-29 09:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Docs: Add model/NOTICE with attribution and changes for the Apache-2.0 weights

Browse Source 
The README already credited AuroraAI-Research and described the ONNX
conversion, but *.md is excluded from the Docker image, so the image shipped
the license without the attribution or the statement of changes that
Apache-2.0 asks for with modified files. model/NOTICE carries both and ships
in the image alongside model/LICENSE.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
multipleof4
2026-10-12 03:06:29 +00:00
co-authored by Claude Opus 5.5
parent efe9971809
commit 967fedfecc
2 changed files with 18 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+3 -1
View File
@@ -50,6 +50,8 @@ curl -H "Authorization: Bearer dev" "localhost:8080/generate?prompt=orange+cat"
## Model and license
`model/` holds an ONNX conversion of [AuroraAI-Research/AuroraIMG-6M](https://huggingface.co/AuroraAI-Research/AuroraIMG-6M) at revision `3d66743`, licensed under the Apache License 2.0 (copy in [`model/LICENSE`](model/LICENSE)). The weights are unchanged; they were converted from the original safetensors to ONNX, and the latent un-normalization and output scaling were folded into `decoder.onnx`. Output matches the original pipeline to within 1/255 per pixel.
`model/` holds an ONNX conversion of [AuroraAI-Research/AuroraIMG-6M](https://huggingface.co/AuroraAI-Research/AuroraIMG-6M) at revision `3d66743`, licensed under the Apache License 2.0 (copy in [`model/LICENSE`](model/LICENSE), attribution and changes in [`model/NOTICE`](model/NOTICE); both ship in the Docker image). The weights are unchanged; they were converted from the original safetensors to ONNX, and the latent un-normalization and output scaling were folded into `decoder.onnx`. Output matches the original pipeline to within 1/255 per pixel.
The model was trained on [CC12M](https://huggingface.co/datasets/pixparse/cc12m-wds), which is distributed as image URLs and captions; the underlying images carry their own licenses.
`scripts/export_onnx.py` regenerates `model/` from the original repo (needs torch, onnx, onnxscript, onnxruntime, safetensors).