kohya-ss / kohya-ss/sd-scripts
Flux merge tool does not properly handle LoRA keys from AI-Toolkit when merging w/ Flux.dev model - All keys "Unused" / Unchanged model file outputted
- Dominant language
- Python
- Stars
- 7.2k
- Forks
- 1.2k
- Avg merge
- 11m
- Merged PRs (30d)
- 2
Description
Hello,
Currently the featuring to merge Flux LoRA into the base model does not function properly with LoRA trained by Ostris' AI-Toolkit. This appears to be due to a difference in the way the keys are labeled/named. The tool does seem able to merge AI-Toolkit LoRA into other Kohya/AI-Toolkit trained LoRA, but merging into the base model fails at the moment.
Thanks for any assistance!
Console example:
```shell
2024-09-18 00:30:17 INFO loading keys from FLUX.1 model: D:/FLUX.1-dev/flux1-dev.safetensors flux_merge_lora.py:55
INFO loading: D:/ai-toolkit/output-mthrbrd/motherboard/motherboard_000005000.safetensors flux_merge_lora.py:74
INFO merging... flux_merge_lora.py:77
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 988/988 [00:00
merge(args)
File "D:\Doctor-SD\Kohya_GUI_Flux_Installer_21\kohya_ss\sd-scripts\networks\flux_merge_lora.py", line 553, in merge
state_dict, metadata = merge_lora_models(args.models, args.ratios, merge_dtype, args.concat, args.shuffle)
File "D:\Doctor-SD\Kohya_GUI_Flux_Installer_21\kohya_ss\sd-scripts\networks\flux_merge_lora.py", line 442, in merge_lora_models
base_alpha = base_alphas[lora_module_name]
KeyError: 'transformer.single_transformer_blocks.0.attn.to_k'
00:33:33-203707 INFO Done merging...
```
Contributor guide
No contributing guide indexed for this repository
Research direction
The failure is in sd-scripts/networks/flux_merge_lora.py, in merge_lora_models and merge; start by reproducing the logged command and tracing the key and alpha lookup around the reported KeyError. Done means AI-Toolkit LoRA keys are recognized when merging into a Flux.dev model without the unused-key warning or KeyError, and the output model is produced.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning, tooling
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100