VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-09 06:45:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update FLUX.1 support for compact models

Browse Source
This commit is contained in:
Kohya S
2024-10-12 21:49:07 +09:00
parent ecaea909b1
commit e277b5789e
4 changed files with 82 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@@ -11,6 +11,16 @@ The command to install PyTorch is as follows:
### Recent Updates
Oct 12, 2024 (update 1):
- [Experimental] FLUX.1 fine-tuning and LoRA training now support "FLUX.1 __compact__" models.
- A compact model is a model that retains the FLUX.1 architecture but reduces the number of double/single blocks from the default 19/38.
- The model is automatically determined based on the keys in *.safetensors.
- Specifications for compact model safetensors:
- Please specify the block indices as consecutive numbers. An error will occur if there are missing numbers. For example, if you reduce the double blocks to 15, the maximum key will be `double_blocks.14.*`. The same applies to single blocks.
- LoRA training is unverified.
- The trained model can be used for inference with `flux_minimal_inference.py`. Other inference environments are unverified.
Oct 12, 2024:
- Multi-GPU training now works on Windows. Thanks to Akegarasu for PR [#1686](https://github.com/kohya-ss/sd-scripts/pull/1686)!