theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-24 01:48:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

add example_dataset in training scripts (#1358)

Browse Source 
* add example_dataset in training scripts

* fix example datasets
This commit is contained in:
Zhongjie Duan
2026-03-18 15:37:03 +08:00
committed by GitHub
parent 4ec4d9c20a
commit ba0626e38f
196 changed files with 911 additions and 567 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
examples/flux2/model_training/full/FLUX.2-klein-4B.sh
View File

@@ -1,6 +1,8 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-4B/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-4B \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-4B/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
@@ -13,9 +15,12 @@ accelerate launch examples/flux2/model_training/train.py \
--use_gradient_checkpointing
# Edit
# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
# accelerate launch examples/flux2/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
# --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
# --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
# --data_file_keys "image,edit_image" \
# --extra_inputs "edit_image" \
# --max_pixels 1048576 \

13
examples/flux2/model_training/full/FLUX.2-klein-9B.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-9B/*" --local_dir ./data/diffsynth_example_dataset
# This script is tested on 8*A100
accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -14,9 +16,12 @@ accelerate launch --config_file examples/flux2/model_training/full/accelerate_co
--use_gradient_checkpointing
# Edit
# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
# accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
# --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
# --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
# --data_file_keys "image,edit_image" \
# --extra_inputs "edit_image" \
# --max_pixels 1048576 \

15
examples/flux2/model_training/full/FLUX.2-klein-base-4B.sh
View File

@@ -1,6 +1,8 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-base-4B/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-4B \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-4B/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
@@ -13,9 +15,12 @@ accelerate launch examples/flux2/model_training/train.py \
--use_gradient_checkpointing
# Edit
# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
# accelerate launch examples/flux2/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
# --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
# --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
# --data_file_keys "image,edit_image" \
# --extra_inputs "edit_image" \
# --max_pixels 1048576 \
@@ -27,4 +32,4 @@ accelerate launch examples/flux2/model_training/train.py \
# --remove_prefix_in_ckpt "pipe.dit." \
# --output_path "./models/train/FLUX.2-klein-base-4B_full" \
# --trainable_models "dit" \
# --use_gradient_checkpointing
# --use_gradient_checkpointing

13
examples/flux2/model_training/full/FLUX.2-klein-base-9B.sh
View File

@@ -1,7 +1,9 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-base-9B/*" --local_dir ./data/diffsynth_example_dataset
# This script is tested on 8*A100
accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-9B \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-9B/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -14,9 +16,12 @@ accelerate launch --config_file examples/flux2/model_training/full/accelerate_co
--use_gradient_checkpointing
# Edit
# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
# accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
# --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
# --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
# --data_file_keys "image,edit_image" \
# --extra_inputs "edit_image" \
# --max_pixels 1048576 \

6
examples/flux2/model_training/lora/FLUX.2-dev.sh
View File

@@ -1,6 +1,8 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-dev/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-dev \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-dev/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 1 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-dev:text_encoder/*.safetensors,black-forest-labs/FLUX.2-dev:vae/diffusion_pytorch_model.safetensors" \

13
examples/flux2/model_training/lora/FLUX.2-klein-4B.sh
View File

@@ -1,6 +1,8 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-4B/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-4B \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-4B/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
@@ -15,9 +17,12 @@ accelerate launch examples/flux2/model_training/train.py \
--use_gradient_checkpointing
# Edit
# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
# accelerate launch examples/flux2/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
# --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
# --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
# --data_file_keys "image,edit_image" \
# --extra_inputs "edit_image" \
# --max_pixels 1048576 \

13
examples/flux2/model_training/lora/FLUX.2-klein-9B.sh
View File

@@ -1,6 +1,8 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-9B/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -15,9 +17,12 @@ accelerate launch examples/flux2/model_training/train.py \
--use_gradient_checkpointing
# Edit
# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
# accelerate launch examples/flux2/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
# --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
# --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
# --data_file_keys "image,edit_image" \
# --extra_inputs "edit_image" \
# --max_pixels 1048576 \

13
examples/flux2/model_training/lora/FLUX.2-klein-base-4B.sh
View File

@@ -1,6 +1,8 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-base-4B/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-4B \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-4B/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
@@ -15,9 +17,12 @@ accelerate launch examples/flux2/model_training/train.py \
--use_gradient_checkpointing
# Edit
# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
# accelerate launch examples/flux2/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
# --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
# --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
# --data_file_keys "image,edit_image" \
# --extra_inputs "edit_image" \
# --max_pixels 1048576 \

15
examples/flux2/model_training/lora/FLUX.2-klein-base-9B.sh
View File

@@ -1,6 +1,8 @@
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-base-9B/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-9B \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-base-9B/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -15,9 +17,12 @@ accelerate launch examples/flux2/model_training/train.py \
--use_gradient_checkpointing
# Edit
# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
# accelerate launch examples/flux2/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
# --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
# --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
# --data_file_keys "image,edit_image" \
# --extra_inputs "edit_image" \
# --max_pixels 1048576 \
@@ -31,4 +36,4 @@ accelerate launch examples/flux2/model_training/train.py \
# --lora_base_model "dit" \
# --lora_target_modules "to_q,to_k,to_v,to_out.0,add_q_proj,add_k_proj,add_v_proj,to_add_out,linear_in,linear_out,to_qkv_mlp_proj,single_transformer_blocks.0.attn.to_out,single_transformer_blocks.1.attn.to_out,single_transformer_blocks.2.attn.to_out,single_transformer_blocks.3.attn.to_out,single_transformer_blocks.4.attn.to_out,single_transformer_blocks.5.attn.to_out,single_transformer_blocks.6.attn.to_out,single_transformer_blocks.7.attn.to_out,single_transformer_blocks.8.attn.to_out,single_transformer_blocks.9.attn.to_out,single_transformer_blocks.10.attn.to_out,single_transformer_blocks.11.attn.to_out,single_transformer_blocks.12.attn.to_out,single_transformer_blocks.13.attn.to_out,single_transformer_blocks.14.attn.to_out,single_transformer_blocks.15.attn.to_out,single_transformer_blocks.16.attn.to_out,single_transformer_blocks.17.attn.to_out,single_transformer_blocks.18.attn.to_out,single_transformer_blocks.19.attn.to_out,single_transformer_blocks.20.attn.to_out,single_transformer_blocks.21.attn.to_out,single_transformer_blocks.22.attn.to_out,single_transformer_blocks.23.attn.to_out" \
# --lora_rank 32 \
# --use_gradient_checkpointing
# --use_gradient_checkpointing

6
examples/flux2/model_training/special/npu_training/FLUX.2-dev-Lora-NPU.sh
View File

@@ -1,9 +1,11 @@
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export CPU_AFFINITY_CONF=1
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-dev/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-dev \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-dev/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 1 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-dev:text_encoder/*.safetensors,black-forest-labs/FLUX.2-dev:vae/diffusion_pytorch_model.safetensors" \

13
examples/flux2/model_training/special/npu_training/FLUX.2-klein-9B-NPU.sh
View File

@@ -2,9 +2,11 @@
export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
export CPU_AFFINITY_CONF=1
modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "flux2/FLUX.2-klein-9B/*" --local_dir ./data/diffsynth_example_dataset
accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata.csv \
--dataset_base_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B \
--dataset_metadata_path data/diffsynth_example_dataset/flux2/FLUX.2-klein-9B/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
@@ -17,9 +19,12 @@ accelerate launch --config_file examples/flux2/model_training/full/accelerate_co
--use_gradient_checkpointing
# Edit
# modelscope download --dataset DiffSynth-Studio/diffsynth_example_dataset --include "qwen_image/Qwen-Image-Edit-2511/*" --local_dir ./data/diffsynth_example_dataset
# accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
# --dataset_base_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511 \
# --dataset_metadata_path data/diffsynth_example_dataset/qwen_image/Qwen-Image-Edit-2511/metadata.json \
# --data_file_keys "image,edit_image" \
# --extra_inputs "edit_image" \
# --max_pixels 1048576 \