theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-23 09:28:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

lora-fix

Browse Source
This commit is contained in:
Artiprocher
2025-08-08 18:55:13 +08:00
parent 051ebf3439
commit 89c4e3bdb6
4 changed files with 1 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/qwen_image/README.md
View File

@@ -247,8 +247,6 @@ The script includes the following parameters:
* `--use_gradient_checkpointing`: Whether to enable gradient checkpointing.
* `--use_gradient_checkpointing_offload`: Whether to offload gradient checkpointing to CPU memory.
* `--gradient_accumulation_steps`: Number of gradient accumulation steps.
* Others
* `--align_to_opensource_format`: Whether to align DiT LoRA format with open-source version. Only works for LoRA training.
In addition, the training framework is built on [`accelerate`](https://huggingface.co/docs/accelerate/index). Run `accelerate config` before training to set GPU-related settings. For some training tasks (e.g., full training of 20B model), we provide suggested `accelerate` config files. Check the corresponding training script for details.