theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-23 00:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add files via upload

Browse Source 
第一版翻译完成，保留了getStart目录，有一些名词还是需要重新检查
This commit is contained in:
yrk111222
2024-10-18 18:02:52 +08:00
committed by GitHub
parent 24b78148b8
commit 883d26abb4
15 changed files with 308 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
docs/source_en/finetune/train_kolors_lora.md
View File

@@ -1,7 +1,5 @@
# 训练 Kolors LoRA
以下文件将用于构建 Kolors。你可以从 [HuggingFace](https://huggingface.co/Kwai-Kolors/Kolors) 或 [ModelScope](https://modelscope.cn/models/Kwai-Kolors/Kolors) 下载 Kolors。由于精度溢出问题，我们需要下载额外的 VAE 模型（从 [HuggingFace](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix) 或 [ModelScope](https://modelscope.cn/models/AI-ModelScope/sdxl-vae-fp16-fix)）。你可以使用以下代码下载这些文件：
# Training Kolors LoRA
The following files will be used to build Kolors. You can download Kolors from [HuggingFace](https://huggingface.co/Kwai-Kolors/Kolors) or [ModelScope](https://modelscope.cn/models/Kwai-Kolors/Kolors). Due to precision overflow issues, we need to download an additional VAE model （from [HuggingFace](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix) or [ModelScope](https://modelscope.cn/models/AI-ModelScope/sdxl-vae-fp16-fix). You can use the following code to download these files:
```python
from diffsynth import download_models
@@ -31,7 +29,7 @@ models
└── diffusion_pytorch_model.safetensors
```
使用下面的命令启动训练任务：
Use the following command to start the training task:
```
CUDA_VISIBLE_DEVICES="0" python examples/train/kolors/train_kolors_lora.py \
@@ -52,9 +50,10 @@ CUDA_VISIBLE_DEVICES="0" python examples/train/kolors/train_kolors_lora.py \
--use_gradient_checkpointing
```
有关参数的更多信息，请使用 `python examples/train/kolors/train_kolors_lora.py -h` 查看详细信息。
For more information on the parameters, please use `python examples/train/kolors/train_kolors_lora.py -h` to view detailed information.
After the training is complete, use `model_manager.load_lora` to load the LoRA for inference.
训练完成后，使用 `model_manager.load_lora` 加载 LoRA 以进行推理。

12
docs/source_en/finetune/train_sd3_lora.md
View File

@@ -1,8 +1,6 @@
# 训练 Stable Diffusion 3 LoRA
训练脚本只需要一个文件。你可以使用 [`sd3_medium_incl_clips.safetensors`](https://huggingface.co/stabilityai/stable-diffusion-3-medium/resolve/main/sd3_medium_incl_clips.safetensors)（没有 T5 Encoder）或 [`sd3_medium_incl_clips_t5xxlfp16.safetensors`](https://huggingface.co/stabilityai/stable-diffusion-3-medium/resolve/main/sd3_medium_incl_clips_t5xxlfp16.safetensors)（有 T5 Encoder）。请使用以下代码下载这些文件：
# Training Stable Diffusion 3 LoRA
The training script only requires one file. You can use [`sd3_medium_incl_clips.safetensors`](https://huggingface.co/stabilityai/stable-diffusion-3-medium/resolve/main/sd3_medium_incl_clips.safetensors)（without T5 Encoder）或 [`sd3_medium_incl_clips_t5xxlfp16.safetensors`](https://huggingface.co/stabilityai/stable-diffusion-3-medium/resolve/main/sd3_medium_incl_clips_t5xxlfp16.safetensors)（with T5 Encoder）. Please use the following code to download these files:
```python
from diffsynth import download_models
@@ -16,7 +14,7 @@ models/stable_diffusion_3/
└── sd3_medium_incl_clips_t5xxlfp16.safetensors
```
使用下面的命令启动训练任务：
Use the following command to start the training task:
```
CUDA_VISIBLE_DEVICES="0" python examples/train/stable_diffusion_3/train_sd3_lora.py \
@@ -35,9 +33,9 @@ CUDA_VISIBLE_DEVICES="0" python examples/train/stable_diffusion_3/train_sd3_lora
--use_gradient_checkpointing
```
有关参数的更多信息，请使用 `python examples/train/stable_diffusion_3/train_sd3_lora.py -h` 查看详细信息。
For more information on the parameters, please use `python examples/train/stable_diffusion_3/train_sd3_lora.py -h` to view detailed information.
训练完成后，使用 `model_manager.load_lora` 加载 LoRA 以进行推理。
After training is completed, use `model_manager.load_lora` to load LoRA for inference.
```python
from diffsynth import ModelManager, SD3ImagePipeline

11
docs/source_en/finetune/train_sd_lora.md
View File

@@ -1,6 +1,6 @@
# 训练 Stable Diffusion LoRA
# Training Stable Diffusion LoRA
训练脚本只需要一个文件。我们支持 [CivitAI](https://civitai.com/) 中的主流检查点。默认情况下，我们使用基础的 Stable Diffusion v1.5。你可以从 [HuggingFace](https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors) 或 [ModelScope](https://www.modelscope.cn/models/AI-ModelScope/stable-diffusion-v1-5/resolve/master/v1-5-pruned-emaonly.safetensors) 下载。你可以使用以下代码下载这个文件：
The training script only requires one file. We support mainstream checkpoints on [CivitAI](https://civitai.com/). By default, we use the basic Stable Diffusion v1.5. You can download it from [HuggingFace](https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.safetensors) or [ModelScope](https://www.modelscope.cn/models/AI-ModelScope/stable-diffusion-v1-5/resolve/master/v1-5-pruned-emaonly.safetensors). You can use the following code to download this file:
```python
from diffsynth import download_models
@@ -14,7 +14,7 @@ models/stable_diffusion
└── v1-5-pruned-emaonly.safetensors
```
使用以下命令启动训练任务：
To initiate the training process, please use the following command:
```
CUDA_VISIBLE_DEVICES="0" python examples/train/stable_diffusion/train_sd_lora.py \
@@ -33,10 +33,9 @@ CUDA_VISIBLE_DEVICES="0" python examples/train/stable_diffusion/train_sd_lora.py
--use_gradient_checkpointing
```
有关参数的更多信息，请使用 `python examples/train/stable_diffusion/train_sd_lora.py -h` 查看详细信息。
训练完成后，使用 `model_manager.load_lora` 加载 LoRA 以进行推理。
For more information about the parameters, please use `python examples/train/stable_diffusion/train_sd_lora.py -h` to view detailed information.
After training is complete, use `model_manager.load_lora` to load LoRA for inference.
```python

12
docs/source_en/finetune/train_sdxl_lora.md
View File

@@ -1,7 +1,7 @@
# 训练 Stable Diffusion XL LoRA
# Training Stable Diffusion XL LoRA
训练脚本只需要一个文件。我们支持 [CivitAI](https://civitai.com/) 中的主流检查点。默认情况下，我们使用基础的 Stable Diffusion XL。你可以从 [HuggingFace](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors) 或 [ModelScope](https://www.modelscope.cn/models/AI-ModelScope/stable-diffusion-xl-base-1.0/resolve/master/sd_xl_base_1.0.safetensors) 下载。也可以使用以下代码下载这个文件：
The training script only requires one file. We support mainstream checkpoints on [CivitAI](https://civitai.com/). By default, we use the basic Stable Diffusion XL. You can download it from [HuggingFace](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/resolve/main/sd_xl_base_1.0.safetensors) 或 [ModelScope](https://www.modelscope.cn/models/AI-ModelScope/stable-diffusion-xl-base-1.0/resolve/master/sd_xl_base_1.0.safetensors). You can also use the following code to download this file:
```python
from diffsynth import download_models
@@ -14,8 +14,7 @@ models/stable_diffusion_xl
└── sd_xl_base_1.0.safetensors
```
我们观察到 Stable Diffusion XL 在 float16 精度下会出现数值精度溢出，因此我们建议用户使用 float32 精度训练，使用以下命令启动训练任务：
We have observed that Stable Diffusion XL may experience numerical precision overflows when using float16 precision, so we recommend that users train with float32 precision. To start the training task, use the following command:
```
CUDA_VISIBLE_DEVICES="0" python examples/train/stable_diffusion_xl/train_sdxl_lora.py \
--pretrained_path models/stable_diffusion_xl/sd_xl_base_1.0.safetensors \
@@ -33,9 +32,10 @@ CUDA_VISIBLE_DEVICES="0" python examples/train/stable_diffusion_xl/train_sdxl_lo
--use_gradient_checkpointing
```
有关参数的更多信息，请使用 `python examples/train/stable_diffusion_xl/train_sdxl_lora.py -h` 查看详细信息。
For more information about the parameters, please use `python examples/train/stable_diffusion_xl/train_sdxl_lora.py -h` to view detailed information.
After training is complete, use `model_manager.load_lora` to load LoRA for inference.
训练完成后，使用 `model_manager.load_lora` 加载 LoRA 以进行推理。
```python
from diffsynth import ModelManager, SDXLImagePipeline