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

Initialize qwen-image on CPU

Browse Source
This commit is contained in:
feng0w0
2026-02-05 11:54:36 +08:00
parent 6886f7ba35
commit fccb1ecdd7
4 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/en/Pipeline_Usage/GPU_support.md
View File

@@ -81,4 +81,5 @@ Set 0 or not set: indicates not enabling the binding function
#### Parameters for specific models
| Model | Parameter | Note |
|----------------|---------------------------|-------------------|
| Wan 14B series | --initialize_model_on_cpu | The 14B model needs to be initialized on the CPU |
| Wan 14B series | --initialize_model_on_cpu | The 14B model needs to be initialized on the CPU |
| Qwen-Image series | --initialize_model_on_cpu | The model needs to be initialized on the CPU |

3
docs/zh/Pipeline_Usage/GPU_support.md
View File

@@ -81,4 +81,5 @@ export CPU_AFFINITY_CONF=1
#### 特定模型需要开启的参数
| 模型 | 参数 | 备注 |
|-----------|------|-------------------|
| Wan 14B系列 | --initialize_model_on_cpu | 14B模型需要在cpu上进行初始化 |
| Wan 14B系列 | --initialize_model_on_cpu | 14B模型需要在cpu上进行初始化 |
| Qwen-Image系列 | --initialize_model_on_cpu | 模型需要在cpu上进行初始化 |

3
examples/qwen_image/model_training/special/npu_training/Qwen-Image-Edit-2509-NPU.sh
View File

@@ -16,4 +16,5 @@ accelerate launch --config_file examples/qwen_image/model_training/full/accelera
--output_path "./models/train/Qwen-Image-Edit-2509_full" \
--trainable_models "dit" \
--use_gradient_checkpointing \
--find_unused_parameters
--find_unused_parameters \
--initialize_model_on_cpu

3
examples/qwen_image/model_training/train.py
View File

@@ -101,6 +101,7 @@ def qwen_image_parser():
parser.add_argument("--tokenizer_path", type=str, default=None, help="Path to tokenizer.")
parser.add_argument("--processor_path", type=str, default=None, help="Path to the processor. If provided, the processor will be used for image editing.")
parser.add_argument("--zero_cond_t", default=False, action="store_true", help="A special parameter introduced by Qwen-Image-Edit-2511. Please enable it for this model.")
parser.add_argument("--initialize_model_on_cpu", default=False, action="store_true", help="Whether to initialize models on CPU.")
return parser
@@ -151,7 +152,7 @@ if __name__ == "__main__":
fp8_models=args.fp8_models,
offload_models=args.offload_models,
task=args.task,
device=accelerator.device,
device="cpu" if args.initialize_model_on_cpu else accelerator.device,
zero_cond_t=args.zero_cond_t,
)
model_logger = ModelLogger(