theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-24 10:18:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into qwen-image-edit

Browse Source
This commit is contained in:
Hong Zhang
2025-08-18 18:56:26 +08:00
committed by GitHub
parent d93de98a21 f11a91e610
commit f9ce261a0e
16 changed files with 282 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh Normal file
View File

@@ -0,0 +1,38 @@
accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config.yaml examples/qwen_image/model_training/train.py \
--dataset_base_path data/example_image_dataset \
--dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_inpaint.csv \
--data_file_keys "image,blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors,DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint:model.safetensors" \
--learning_rate 1e-4 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.blockwise_controlnet.models.0." \
--output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Inpaint_full" \
--trainable_models "blockwise_controlnet" \
--extra_inputs "blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
--use_gradient_checkpointing \
--find_unused_parameters
# If you want to pre-train a Inpaint Blockwise ControlNet from scratch,
# please run the following script to first generate the initialized model weights file,
# and then start training with a high learning rate (1e-3).
# python examples/qwen_image/model_training/scripts/Qwen-Image-Blockwise-ControlNet-Inpaint-Initialize.py
# accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config.yaml examples/qwen_image/model_training/train.py \
# --dataset_base_path data/example_image_dataset \
# --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_inpaint.csv \
# --data_file_keys "image,blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
# --max_pixels 1048576 \
# --dataset_repeat 50 \
# --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
# --model_paths '["models/blockwise_controlnet_inpaint.safetensors"]' \
# --learning_rate 1e-3 \
# --num_epochs 2 \
# --remove_prefix_in_ckpt "pipe.blockwise_controlnet.models.0." \
# --output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Inpaint_full" \
# --trainable_models "blockwise_controlnet" \
# --extra_inputs "blockwise_controlnet_image,blockwise_controlnet_inpaint_mask" \
# --use_gradient_checkpointing \
# --find_unused_parameters

22
examples/qwen_image/model_training/full/accelerate_config.yaml Normal file
View File

@@ -0,0 +1,22 @@
compute_environment: LOCAL_MACHINE
debug: false
deepspeed_config:
gradient_accumulation_steps: 1
offload_optimizer_device: none
offload_param_device: none
zero3_init_flag: false
zero_stage: 2
distributed_type: DEEPSPEED
downcast_bf16: 'no'
enable_cpu_affinity: false
machine_rank: 0
main_training_function: main
mixed_precision: bf16
num_machines: 1
num_processes: 8
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false