theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-23 17:38:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

align flux lora format (#204)

Browse Source
This commit is contained in:
Zhongjie Duan
2024-09-12 16:01:27 +08:00
committed by GitHub
parent 0b9e673fa2
commit a8cb4a21d1
4 changed files with 71 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/train/README.md
View File

@@ -142,9 +142,12 @@ CUDA_VISIBLE_DEVICES="0" python examples/train/flux/train_flux_lora.py \
--learning_rate 1e-4 \
--lora_rank 4 \
--lora_alpha 4 \
--use_gradient_checkpointing
--use_gradient_checkpointing \
--align_to_opensource_format
```
**`--align_to_opensource_format` means that this script will export the LoRA weights in the opensource format. This format can be loaded in both DiffSynth-Studio and other codebases.**
For more information about the parameters, please use `python examples/train/flux/train_flux_lora.py -h` to see the details.
After training, use `model_manager.load_lora` to load the LoRA for inference.
@@ -165,7 +168,7 @@ pipe = SDXLImagePipeline.from_model_manager(model_manager)
torch.manual_seed(0)
image = pipe(
prompt=prompt,
prompt="a dog is jumping, flowers around the dog, the background is mountains and clouds",
num_inference_steps=30, embedded_guidance=3.5
)
image.save("image_with_lora.jpg")