theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-19 06:39:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix bugs

Browse Source
This commit is contained in:
Artiprocher
2024-08-02 13:47:07 +08:00
parent f189f9f1be
commit 6877b460c4
2 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
diffsynth/controlnets/processors.py
View File

@@ -47,6 +47,5 @@ class Annotator:
detect_resolution = self.detect_resolution if self.detect_resolution is not None else min(width, height)
image = self.processor(image, detect_resolution=detect_resolution, image_resolution=min(width, height), **kwargs)
image = image.resize((width, height))
image.save("/mnt/zhongjie/DiffSynth-Studio-kolors/DiffSynth-Studio/input.jpg")
return image

6
examples/train/README.md
View File

@@ -13,6 +13,12 @@ Image Examples of fine-tuned LoRA. The prompt is "一只小狗蹦蹦跳跳，周
|Without LoRA|![image_without_lora](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/9d79ed7a-e8cf-4d98-800a-f182809db318)|![image_without_lora](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/ddb834a5-6366-412b-93dc-6d957230d66e)|![image_without_lora](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/1aa21de5-a992-4b66-b14f-caa44e08876e)|
|With LoRA|![image_with_lora](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/02f62323-6ee5-4788-97a1-549732dbe4f0)|![image_with_lora](https://github.com/modelscope/DiffSynth-Studio/assets/35051019/8e7b2888-d874-4da4-a75b-11b6b214b9bf)|![image_with_lora](https://github.com/Artiprocher/DiffSynth-Studio/assets/35051019/83a0a41a-691f-4610-8e7b-d8e17c50a282)|
## Install additional packages
```
pip install peft lightning
```
## Prepare your dataset
We provide an example dataset [here](https://modelscope.cn/datasets/buptwq/lora-stable-diffusion-finetune/files). You need to manage the training images as follows: