theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #735 from modelscope/qwen-image

Browse Source 
qwen-image
This commit is contained in:
Zhongjie Duan
2025-08-04 20:40:32 +08:00
committed by GitHub
parent a8ee7ec9ef 1625894694
commit 8d2f6ad32e
21 changed files with 2903 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
diffsynth/trainers/utils.py
View File

@@ -475,3 +475,32 @@ def flux_parser():
parser.add_argument("--use_gradient_checkpointing_offload", default=False, action="store_true", help="Whether to offload gradient checkpointing to CPU memory.")
parser.add_argument("--gradient_accumulation_steps", type=int, default=1, help="Gradient accumulation steps.")
return parser
def qwen_image_parser():
parser = argparse.ArgumentParser(description="Simple example of a training script.")
parser.add_argument("--dataset_base_path", type=str, default="", required=True, help="Base path of the dataset.")
parser.add_argument("--dataset_metadata_path", type=str, default=None, help="Path to the metadata file of the dataset.")
parser.add_argument("--max_pixels", type=int, default=1024*1024, help="Maximum number of pixels per frame, used for dynamic resolution..")
parser.add_argument("--height", type=int, default=None, help="Height of images. Leave `height` and `width` empty to enable dynamic resolution.")
parser.add_argument("--width", type=int, default=None, help="Width of images. Leave `height` and `width` empty to enable dynamic resolution.")
parser.add_argument("--data_file_keys", type=str, default="image", help="Data file keys in the metadata. Comma-separated.")
parser.add_argument("--dataset_repeat", type=int, default=1, help="Number of times to repeat the dataset per epoch.")
parser.add_argument("--model_paths", type=str, default=None, help="Paths to load models. In JSON format.")
parser.add_argument("--model_id_with_origin_paths", type=str, default=None, help="Model ID with origin paths, e.g., Wan-AI/Wan2.1-T2V-1.3B:diffusion_pytorch_model*.safetensors. Comma-separated.")
parser.add_argument("--tokenizer_path", type=str, default=None, help="Paths to tokenizer.")
parser.add_argument("--learning_rate", type=float, default=1e-4, help="Learning rate.")
parser.add_argument("--num_epochs", type=int, default=1, help="Number of epochs.")
parser.add_argument("--output_path", type=str, default="./models", help="Output save path.")
parser.add_argument("--remove_prefix_in_ckpt", type=str, default="pipe.dit.", help="Remove prefix in ckpt.")
parser.add_argument("--trainable_models", type=str, default=None, help="Models to train, e.g., dit, vae, text_encoder.")
parser.add_argument("--lora_base_model", type=str, default=None, help="Which model LoRA is added to.")
parser.add_argument("--lora_target_modules", type=str, default="q,k,v,o,ffn.0,ffn.2", help="Which layers LoRA is added to.")
parser.add_argument("--lora_rank", type=int, default=32, help="Rank of LoRA.")
parser.add_argument("--extra_inputs", default=None, help="Additional model inputs, comma-separated.")
parser.add_argument("--align_to_opensource_format", default=False, action="store_true", help="Whether to align the lora format to opensource format. Only for DiT's LoRA.")
parser.add_argument("--use_gradient_checkpointing", default=False, action="store_true", help="Whether to use gradient checkpointing.")
parser.add_argument("--use_gradient_checkpointing_offload", default=False, action="store_true", help="Whether to offload gradient checkpointing to CPU memory.")
parser.add_argument("--gradient_accumulation_steps", type=int, default=1, help="Gradient accumulation steps.")
return parser