theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-04-14 21:58:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

support ernie-image-turbo (#1391)

Browse Source 
* support ernie-image-turbo

* pr review fix

* fix modelname
This commit is contained in:
Hong Zhang
2026-04-14 11:35:43 +08:00
committed by GitHub
parent 960d8c62c0
commit b5d04ceb30
18 changed files with 142 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/ernie_image/model_training/full/Ernie-Image-T2I.sh → examples/ernie_image/model_training/full/ERNIE-Image.sh
View File

@@ -6,7 +6,7 @@ accelerate launch --config_file examples/ernie_image/model_training/full/acceler
--dataset_metadata_path data/diffsynth_example_dataset/ernie_image/Ernie-Image-T2I/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "baidu/ERNIE-Image:transformer/diffusion_pytorch_model*.safetensors,baidu/ERNIE-Image:text_encoder/model.safetensors,baidu/ERNIE-Image:vae/diffusion_pytorch_model.safetensors" \
--model_id_with_origin_paths "PaddlePaddle/ERNIE-Image:transformer/diffusion_pytorch_model*.safetensors,PaddlePaddle/ERNIE-Image:text_encoder/model.safetensors,PaddlePaddle/ERNIE-Image:vae/diffusion_pytorch_model.safetensors" \
--learning_rate 1e-5 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.dit." \

2
examples/ernie_image/model_training/lora/Ernie-Image-T2I.sh → examples/ernie_image/model_training/lora/ERNIE-Image.sh
View File

@@ -6,7 +6,7 @@ accelerate launch examples/ernie_image/model_training/train.py \
--dataset_metadata_path data/diffsynth_example_dataset/ernie_image/Ernie-Image-T2I/metadata.csv \
--max_pixels 1048576 \
--dataset_repeat 50 \
--model_id_with_origin_paths "baidu/ERNIE-Image:transformer/diffusion_pytorch_model*.safetensors,baidu/ERNIE-Image:text_encoder/model.safetensors,baidu/ERNIE-Image:vae/diffusion_pytorch_model.safetensors" \
--model_id_with_origin_paths "PaddlePaddle/ERNIE-Image:transformer/diffusion_pytorch_model*.safetensors,PaddlePaddle/ERNIE-Image:text_encoder/model.safetensors,PaddlePaddle/ERNIE-Image:vae/diffusion_pytorch_model.safetensors" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \

2
examples/ernie_image/model_training/train.py
View File

@@ -25,7 +25,7 @@ class ErnieImageTrainingModule(DiffusionTrainingModule):
super().__init__()
# Load models
model_configs = self.parse_model_configs(model_paths, model_id_with_origin_paths, fp8_models=fp8_models, offload_models=offload_models, device=device)
tokenizer_config = ModelConfig(model_id="baidu/ERNIE-Image", origin_file_pattern="tokenizer/") if tokenizer_path is None else ModelConfig(tokenizer_path)
tokenizer_config = ModelConfig(model_id="PaddlePaddle/ERNIE-Image", origin_file_pattern="tokenizer/") if tokenizer_path is None else ModelConfig(tokenizer_path)
self.pipe = ErnieImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device=device, model_configs=model_configs, tokenizer_config=tokenizer_config)
self.pipe = self.split_pipeline_units(task, self.pipe, trainable_models, lora_base_model)

6
examples/ernie_image/model_training/validate_full/Ernie-Image-T2I.py → examples/ernie_image/model_training/validate_full/ERNIE-Image.py
View File

@@ -6,9 +6,9 @@ pipe = ErnieImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="baidu/ERNIE-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
ModelConfig(model_id="baidu/ERNIE-Image", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="baidu/ERNIE-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
ModelConfig(model_id="PaddlePaddle/ERNIE-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
ModelConfig(model_id="PaddlePaddle/ERNIE-Image", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="PaddlePaddle/ERNIE-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
],
)

6
examples/ernie_image/model_training/validate_lora/Ernie-Image-T2I.py → examples/ernie_image/model_training/validate_lora/ERNIE-Image.py
View File

@@ -6,9 +6,9 @@ pipe = ErnieImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="baidu/ERNIE-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
ModelConfig(model_id="baidu/ERNIE-Image", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="baidu/ERNIE-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
ModelConfig(model_id="PaddlePaddle/ERNIE-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
ModelConfig(model_id="PaddlePaddle/ERNIE-Image", origin_file_pattern="text_encoder/model.safetensors"),
ModelConfig(model_id="PaddlePaddle/ERNIE-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
],
)