theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-19 06:23:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

kontext training

Browse Source
This commit is contained in:
Artiprocher
2025-06-30 11:00:10 +08:00
parent 44e2eecdf1
commit 157e0be49d
4 changed files with 46 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/flux/README.md
View File

@@ -1,6 +1,6 @@
# FLUX
[Switch to Chinese](./README_zh.md)
[切换到中文](./README_zh.md)
FLUX is a series of image generation models open-sourced by Black-Forest-Labs.
@@ -44,9 +44,9 @@ image.save("image.jpg")
**Support for the new framework of the FLUX series models is under active development. Stay tuned!**
| Model ID | Additional Parameters | Inference | Full Training | Validation After Full Training | LoRA Training | Validation After LoRA Training |
|---------|------------------------|-----------|---------------|-------------------------------|---------------|--------------------------------|
| [black-forest-labs/FLUX.1-dev](https://modelscope.cn/models/black-forest-labs/FLUX.1-dev) | | [code](./model_inference/FLUX.1-dev.py) | [code](./model_training/full/FLUX.1-dev.sh) | [code](./model_training/validate_full/FLUX.1-dev.py) | [code](./model_training/lora/FLUX.1-dev.sh) | [code](./model_training/validate_lora/FLUX.1-dev.py) |
| [black-forest-labs/FLUX.1-Kontext-dev](https://modelscope.cn/models/black-forest-labs/FLUX.1-Kontext-dev) | `kontext_images` | [code](./model_inference/FLUX.1-Kontext-dev.py) | | | [code](./model_training/lora/FLUX.1-Kontext-dev.sh) | [code](./model_training/validate_lora/FLUX.1-Kontext-dev.py) |
|-|-|-|-|-|-|-|
|[black-forest-labs/FLUX.1-dev](https://modelscope.cn/models/black-forest-labs/FLUX.1-dev)||[code](./model_inference/FLUX.1-dev.py)|[code](./model_training/full/FLUX.1-dev.sh)|[code](./model_training/validate_full/FLUX.1-dev.py)|[code](./model_training/lora/FLUX.1-dev.sh)|[code](./model_training/validate_lora/FLUX.1-dev.py)|
|[black-forest-labs/FLUX.1-Kontext-dev](https://modelscope.cn/models/black-forest-labs/FLUX.1-Kontext-dev)|`kontext_images`|[code](./model_inference/FLUX.1-Kontext-dev.py)|[code](./model_training/full/FLUX.1-Kontext-dev.sh)|[code](./model_training/validate_full/FLUX.1-Kontext-dev.py)|[code](./model_training/lora/FLUX.1-Kontext-dev.sh)|[code](./model_training/validate_lora/FLUX.1-Kontext-dev.py)|
## Model Inference

4
examples/flux/README_zh.md
View File

@@ -46,7 +46,7 @@ image.save("image.jpg")
|模型 ID|额外参数|推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证|
|-|-|-|-|-|-|-|
|[black-forest-labs/FLUX.1-dev](https://modelscope.cn/models/black-forest-labs/FLUX.1-dev)||[code](./model_inference/FLUX.1-dev.py)|[code](./model_training/full/FLUX.1-dev.sh)|[code](./model_training/validate_full/FLUX.1-dev.py)|[code](./model_training/lora/FLUX.1-dev.sh)|[code](./model_training/validate_lora/FLUX.1-dev.py)|
|[black-forest-labs/FLUX.1-Kontext-dev](https://modelscope.cn/models/black-forest-labs/FLUX.1-Kontext-dev)|`kontext_images`|[code](./model_inference/FLUX.1-Kontext-dev.py)|||[code](./model_training/lora/FLUX.1-Kontext-dev.sh)|[code](./model_training/validate_lora/FLUX.1-Kontext-dev.py)|
|[black-forest-labs/FLUX.1-Kontext-dev](https://modelscope.cn/models/black-forest-labs/FLUX.1-Kontext-dev)|`kontext_images`|[code](./model_inference/FLUX.1-Kontext-dev.py)|[code](./model_training/full/FLUX.1-Kontext-dev.sh)|[code](./model_training/validate_full/FLUX.1-Kontext-dev.py)|[code](./model_training/lora/FLUX.1-Kontext-dev.sh)|[code](./model_training/validate_lora/FLUX.1-Kontext-dev.py)|
## 模型推理
@@ -252,7 +252,7 @@ video,prompt,kontext_images
image1.jpg,"a cat is sleeping",image1_reference.jpg
```
额外输入若包含视频和图像文件，则需要在 `--data_file_keys` 参数中指定要解析的列名。可根据额外输入增加相应的列名，例如 `--data_file_keys "image,kontext_images"`。
额外输入若包含视频和图像文件，则需要在 `--data_file_keys` 参数中指定要解析的列名。可根据额外输入增加相应的列名，例如 `--data_file_keys "image,kontext_images"`，同时启用 `--extra_inputs "kontext_images"`。
</details>

14
examples/flux/model_training/full/FLUX.1-Kontext-dev.sh Normal file
View File

@@ -0,0 +1,14 @@
accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata_kontext.csv \
--data_file_keys "image,kontext_images" \
--max_pixels 1048576 \
--dataset_repeat 400 \
--model_id_with_origin_paths "black-forest-labs/FLUX.1-Kontext-dev:flux1-kontext-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
--learning_rate 1e-5 \
--num_epochs 1 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/FLUX.1-Kontext-dev_full" \
--trainable_models "dit" \
--extra_inputs "kontext_images" \
--use_gradient_checkpointing

26
examples/flux/model_training/validate_full/FLUX.1-Kontext-dev.py Normal file
View File

@@ -0,0 +1,26 @@
import torch
from diffsynth.pipelines.flux_image_new import FluxImagePipeline, ModelConfig
from diffsynth import load_state_dict
from PIL import Image
pipe = FluxImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="black-forest-labs/FLUX.1-Kontext-dev", origin_file_pattern="flux1-kontext-dev.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/"),
ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
],
)
state_dict = load_state_dict("models/train/FLUX.1-Kontext-dev_full/epoch-0.safetensors")
pipe.dit.load_state_dict(state_dict)
image = pipe(
prompt="Make the dog turn its head around.",
kontext_images=Image.open("data/example_image_dataset/2.jpg").resize((768, 768)),
height=768, width=768,
seed=0
)
image.save("image_FLUX.1-Kontext-dev_full.jpg")