diffsynth 2.0.3__tar.gz → 2.0.4__tar.gz

{diffsynth-2.0.3/diffsynth.egg-info → diffsynth-2.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diffsynth
-Version: 2.0.3
+Version: 2.0.4
 Summary: Enjoy the magic of Diffusion models!
 Author: ModelScope Team
 License: Apache-2.0

{diffsynth-2.0.3 → diffsynth-2.0.4}/README.md

@@ -33,6 +33,8 @@ We believe that a well-developed open-source code framework can lower the thresh
 
 > Currently, the development personnel of this project are limited, with most of the work handled by [Artiprocher](https://github.com/Artiprocher). Therefore, the progress of new feature development will be relatively slow, and the speed of responding to and resolving issues is limited. We apologize for this and ask developers to understand.
 
+- **January 27, 2026**: [Z-Image](https://modelscope.cn/models/Tongyi-MAI/Z-Image) is released, and our [Z-Image-i2L](https://www.modelscope.cn/models/DiffSynth-Studio/Z-Image-i2L) model is released concurrently. You can use it in [ModelScope Studios](https://modelscope.cn/studios/DiffSynth-Studio/Z-Image-i2L). For details, see the [documentation](/docs/zh/Model_Details/Z-Image.md).
+
 - **January 19, 2026**: Added support for [FLUX.2-klein-4B](https://modelscope.cn/models/black-forest-labs/FLUX.2-klein-4B) and [FLUX.2-klein-9B](https://modelscope.cn/models/black-forest-labs/FLUX.2-klein-9B) models, including training and inference capabilities. [Documentation](/docs/en/Model_Details/FLUX2.md) and [example code](/examples/flux2/) are now available.
 
 - **January 12, 2026**: We trained and open-sourced a text-guided image layer separation model ([Model Link](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Layered-Control)). Given an input image and a textual description, the model isolates the image layer corresponding to the described content. For more details, please refer to our blog post ([Chinese version](https://modelscope.cn/learn/4938), [English version](https://huggingface.co/blog/kelseye/qwen-image-layered-control)).
@@ -269,9 +271,14 @@ image.save("image.jpg")
 
 Example code for Z-Image is available at: [/examples/z_image/](/examples/z_image/)
 
-| Model ID | Inference | Low-VRAM Inference | Full Training | Full Training Validation | LoRA Training | LoRA Training Validation |
+|Model ID|Inference|Low VRAM Inference|Full Training|Validation After Full Training|LoRA Training|Validation After LoRA Training|
 |-|-|-|-|-|-|-|
+|[Tongyi-MAI/Z-Image](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image)|[code](/examples/z_image/model_inference/Z-Image.py)|[code](/examples/z_image/model_inference_low_vram/Z-Image.py)|[code](/examples/z_image/model_training/full/Z-Image.sh)|[code](/examples/z_image/model_training/validate_full/Z-Image.py)|[code](/examples/z_image/model_training/lora/Z-Image.sh)|[code](/examples/z_image/model_training/validate_lora/Z-Image.py)|
+|[DiffSynth-Studio/Z-Image-i2L](https://www.modelscope.cn/models/DiffSynth-Studio/Z-Image-i2L)|[code](/examples/z_image/model_inference/Z-Image-i2L.py)|[code](/examples/z_image/model_inference_low_vram/Z-Image-i2L.py)|-|-|-|-|
 |[Tongyi-MAI/Z-Image-Turbo](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo)|[code](/examples/z_image/model_inference/Z-Image-Turbo.py)|[code](/examples/z_image/model_inference_low_vram/Z-Image-Turbo.py)|[code](/examples/z_image/model_training/full/Z-Image-Turbo.sh)|[code](/examples/z_image/model_training/validate_full/Z-Image-Turbo.py)|[code](/examples/z_image/model_training/lora/Z-Image-Turbo.sh)|[code](/examples/z_image/model_training/validate_lora/Z-Image-Turbo.py)|
+|[PAI/Z-Image-Turbo-Fun-Controlnet-Union-2.1](https://www.modelscope.cn/models/PAI/Z-Image-Turbo-Fun-Controlnet-Union-2.1)|[code](/examples/z_image/model_inference/Z-Image-Turbo-Fun-Controlnet-Union-2.1.py)|[code](/examples/z_image/model_inference_low_vram/Z-Image-Turbo-Fun-Controlnet-Union-2.1.py)|[code](/examples/z_image/model_training/full/Z-Image-Turbo-Fun-Controlnet-Union-2.1.sh)|[code](/examples/z_image/model_training/validate_full/Z-Image-Turbo-Fun-Controlnet-Union-2.1.py)|[code](/examples/z_image/model_training/lora/Z-Image-Turbo-Fun-Controlnet-Union-2.1.sh)|[code](/examples/z_image/model_training/validate_lora/Z-Image-Turbo-Fun-Controlnet-Union-2.1.py)|
+|[PAI/Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps](https://www.modelscope.cn/models/PAI/Z-Image-Turbo-Fun-Controlnet-Union-2.1)|[code](/examples/z_image/model_inference/Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps.py)|[code](/examples/z_image/model_inference_low_vram/Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps.py)|[code](/examples/z_image/model_training/full/Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps.sh)|[code](/examples/z_image/model_training/validate_full/Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps.py)|[code](/examples/z_image/model_training/lora/Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps.sh)|[code](/examples/z_image/model_training/validate_lora/Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps.py)|
+|[PAI/Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps](https://www.modelscope.cn/models/PAI/Z-Image-Turbo-Fun-Controlnet-Union-2.1)|[code](/examples/z_image/model_inference/Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps.py)|[code](/examples/z_image/model_inference_low_vram/Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps.py)|[code](/examples/z_image/model_training/full/Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps.sh)|[code](/examples/z_image/model_training/validate_full/Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps.py)|[code](/examples/z_image/model_training/lora/Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps.sh)|[code](/examples/z_image/model_training/validate_lora/Z-Image-Turbo-Fun-Controlnet-Tile-2.1-8steps.py)|
 
 </details>
 

{diffsynth-2.0.3 → diffsynth-2.0.4}/diffsynth/core/loader/config.py

@@ -1,5 +1,5 @@
 import torch, glob, os
-from typing import Optional, Union
+from typing import Optional, Union, Dict
 from dataclasses import dataclass
 from modelscope import snapshot_download
 from huggingface_hub import snapshot_download as hf_snapshot_download
@@ -23,6 +23,7 @@ class ModelConfig:
     computation_device: Optional[Union[str, torch.device]] = None
     computation_dtype: Optional[torch.dtype] = None
     clear_parameters: bool = False
+    state_dict: Dict[str, torch.Tensor] = None
     
     def check_input(self):
         if self.path is None and self.model_id is None:

{diffsynth-2.0.3 → diffsynth-2.0.4}/diffsynth/core/loader/file.py

@@ -2,16 +2,25 @@ from safetensors import safe_open
 import torch, hashlib
 
 
-def load_state_dict(file_path, torch_dtype=None, device="cpu"):
+def load_state_dict(file_path, torch_dtype=None, device="cpu", pin_memory=False, verbose=0):
     if isinstance(file_path, list):
         state_dict = {}
         for file_path_ in file_path:
-            state_dict.update(load_state_dict(file_path_, torch_dtype, device))
-        return state_dict
-    if file_path.endswith(".safetensors"):
-        return load_state_dict_from_safetensors(file_path, torch_dtype=torch_dtype, device=device)
+            state_dict.update(load_state_dict(file_path_, torch_dtype, device, pin_memory=pin_memory, verbose=verbose))
     else:
-        return load_state_dict_from_bin(file_path, torch_dtype=torch_dtype, device=device)
+        if verbose >= 1:
+            print(f"Loading file [started]: {file_path}")
+        if file_path.endswith(".safetensors"):
+            state_dict = load_state_dict_from_safetensors(file_path, torch_dtype=torch_dtype, device=device)
+        else:
+            state_dict = load_state_dict_from_bin(file_path, torch_dtype=torch_dtype, device=device)
+        # If load state dict in CPU memory, `pin_memory=True` will make `model.to("cuda")` faster.
+        if pin_memory:
+            for i in state_dict:
+                state_dict[i] = state_dict[i].pin_memory()
+        if verbose >= 1:
+            print(f"Loading file [done]: {file_path}")
+    return state_dict
 
 
 def load_state_dict_from_safetensors(file_path, torch_dtype=None, device="cpu"):

{diffsynth-2.0.3 → diffsynth-2.0.4}/diffsynth/core/loader/model.py

@@ -5,7 +5,7 @@ from .file import load_state_dict
 import torch
 
 
-def load_model(model_class, path, config=None, torch_dtype=torch.bfloat16, device="cpu", state_dict_converter=None, use_disk_map=False, module_map=None, vram_config=None, vram_limit=None):
+def load_model(model_class, path, config=None, torch_dtype=torch.bfloat16, device="cpu", state_dict_converter=None, use_disk_map=False, module_map=None, vram_config=None, vram_limit=None, state_dict=None):
     config = {} if config is None else config
     # Why do we use `skip_model_initialization`?
     # It skips the random initialization of model parameters,
@@ -20,7 +20,7 @@ def load_model(model_class, path, config=None, torch_dtype=torch.bfloat16, devic
         dtypes = [vram_config["offload_dtype"], vram_config["onload_dtype"], vram_config["preparing_dtype"], vram_config["computation_dtype"]]
         dtype = [d for d in dtypes if d != "disk"][0]
         if vram_config["offload_device"] != "disk":
-            state_dict = DiskMap(path, device, torch_dtype=dtype)
+            if state_dict is None: state_dict = DiskMap(path, device, torch_dtype=dtype)
             if state_dict_converter is not None:
                 state_dict = state_dict_converter(state_dict)
             else:
@@ -35,7 +35,9 @@ def load_model(model_class, path, config=None, torch_dtype=torch.bfloat16, devic
         # Sometimes a model file contains multiple models,
         # and DiskMap can load only the parameters of a single model,
         # avoiding the need to load all parameters in the file.
-        if use_disk_map:
+        if state_dict is not None:
+            pass
+        elif use_disk_map:
             state_dict = DiskMap(path, device, torch_dtype=torch_dtype)
         else:
             state_dict = load_state_dict(path, torch_dtype, device)

{diffsynth-2.0.3 → diffsynth-2.0.4}/diffsynth/diffusion/base_pipeline.py

@@ -296,6 +296,7 @@ class BasePipeline(torch.nn.Module):
                 vram_config=vram_config,
                 vram_limit=vram_limit,
                 clear_parameters=model_config.clear_parameters,
+                state_dict=model_config.state_dict,
             )
         return model_pool
     

{diffsynth-2.0.3 → diffsynth-2.0.4}/diffsynth/models/model_loader.py

@@ -29,7 +29,7 @@ class ModelPool:
             module_map = None
         return module_map
     
-    def load_model_file(self, config, path, vram_config, vram_limit=None):
+    def load_model_file(self, config, path, vram_config, vram_limit=None, state_dict=None):
         model_class = self.import_model_class(config["model_class"])
         model_config = config.get("extra_kwargs", {})
         if "state_dict_converter" in config:
@@ -43,6 +43,7 @@ class ModelPool:
             state_dict_converter,
             use_disk_map=True,
             vram_config=vram_config, module_map=module_map, vram_limit=vram_limit,
+            state_dict=state_dict,
         )
         return model
     
@@ -59,7 +60,7 @@ class ModelPool:
         }
         return vram_config
     
-    def auto_load_model(self, path, vram_config=None, vram_limit=None, clear_parameters=False):
+    def auto_load_model(self, path, vram_config=None, vram_limit=None, clear_parameters=False, state_dict=None):
         print(f"Loading models from: {json.dumps(path, indent=4)}")
         if vram_config is None:
             vram_config = self.default_vram_config()
@@ -67,7 +68,7 @@ class ModelPool:
         loaded = False
         for config in MODEL_CONFIGS:
             if config["model_hash"] == model_hash:
-                model = self.load_model_file(config, path, vram_config, vram_limit=vram_limit)
+                model = self.load_model_file(config, path, vram_config, vram_limit=vram_limit, state_dict=state_dict)
                 if clear_parameters: self.clear_parameters(model)
                 self.model.append(model)
                 model_name = config["model_name"]

{diffsynth-2.0.3 → diffsynth-2.0.4}/diffsynth/pipelines/flux2_image.py

@@ -1,4 +1,4 @@
-import torch, math
+import torch, math, torchvision
 from PIL import Image
 from typing import Union
 from tqdm import tqdm
@@ -477,10 +477,21 @@ class Flux2Unit_EditImageEmbedder(PipelineUnit):
         width = round(width / 32) * 32
         height = round(height / 32) * 32
         return width, height
+    
+    def crop_and_resize(self, image, target_height, target_width):
+        width, height = image.size
+        scale = max(target_width / width, target_height / height)
+        image = torchvision.transforms.functional.resize(
+            image,
+            (round(height*scale), round(width*scale)),
+            interpolation=torchvision.transforms.InterpolationMode.BILINEAR
+        )
+        image = torchvision.transforms.functional.center_crop(image, (target_height, target_width))
+        return image
 
     def edit_image_auto_resize(self, edit_image):
         calculated_width, calculated_height = self.calculate_dimensions(1024 * 1024, edit_image.size[0] / edit_image.size[1])
-        return edit_image.resize((calculated_width, calculated_height))
+        return self.crop_and_resize(edit_image, calculated_height, calculated_width)
     
     def process_image_ids(self, image_latents, scale=10):
         t_coords = [scale + scale * t for t in torch.arange(0, len(image_latents))]

{diffsynth-2.0.3 → diffsynth-2.0.4/diffsynth.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diffsynth
-Version: 2.0.3
+Version: 2.0.4
 Summary: Enjoy the magic of Diffusion models!
 Author: ModelScope Team
 License: Apache-2.0

diffsynth-2.0.4/diffsynth.egg-info/SOURCES.txt

@@ -0,0 +1,119 @@
+LICENSE
+README.md
+pyproject.toml
+diffsynth/__init__.py
+diffsynth.egg-info/PKG-INFO
+diffsynth.egg-info/SOURCES.txt
+diffsynth.egg-info/dependency_links.txt
+diffsynth.egg-info/requires.txt
+diffsynth.egg-info/top_level.txt
+diffsynth/configs/__init__.py
+diffsynth/configs/model_configs.py
+diffsynth/configs/vram_management_module_maps.py
+diffsynth/core/__init__.py
+diffsynth/core/attention/__init__.py
+diffsynth/core/attention/attention.py
+diffsynth/core/data/__init__.py
+diffsynth/core/data/operators.py
+diffsynth/core/data/unified_dataset.py
+diffsynth/core/device/__init__.py
+diffsynth/core/device/npu_compatible_device.py
+diffsynth/core/gradient/__init__.py
+diffsynth/core/gradient/gradient_checkpoint.py
+diffsynth/core/loader/__init__.py
+diffsynth/core/loader/config.py
+diffsynth/core/loader/file.py
+diffsynth/core/loader/model.py
+diffsynth/core/vram/__init__.py
+diffsynth/core/vram/disk_map.py
+diffsynth/core/vram/initialization.py
+diffsynth/core/vram/layers.py
+diffsynth/diffusion/__init__.py
+diffsynth/diffusion/base_pipeline.py
+diffsynth/diffusion/flow_match.py
+diffsynth/diffusion/logger.py
+diffsynth/diffusion/loss.py
+diffsynth/diffusion/parsers.py
+diffsynth/diffusion/runner.py
+diffsynth/diffusion/training_module.py
+diffsynth/models/dinov3_image_encoder.py
+diffsynth/models/flux2_dit.py
+diffsynth/models/flux2_text_encoder.py
+diffsynth/models/flux2_vae.py
+diffsynth/models/flux_controlnet.py
+diffsynth/models/flux_dit.py
+diffsynth/models/flux_infiniteyou.py
+diffsynth/models/flux_ipadapter.py
+diffsynth/models/flux_lora_encoder.py
+diffsynth/models/flux_lora_patcher.py
+diffsynth/models/flux_text_encoder_clip.py
+diffsynth/models/flux_text_encoder_t5.py
+diffsynth/models/flux_vae.py
+diffsynth/models/flux_value_control.py
+diffsynth/models/general_modules.py
+diffsynth/models/longcat_video_dit.py
+diffsynth/models/model_loader.py
+diffsynth/models/nexus_gen.py
+diffsynth/models/nexus_gen_ar_model.py
+diffsynth/models/nexus_gen_projector.py
+diffsynth/models/qwen_image_controlnet.py
+diffsynth/models/qwen_image_dit.py
+diffsynth/models/qwen_image_image2lora.py
+diffsynth/models/qwen_image_text_encoder.py
+diffsynth/models/qwen_image_vae.py
+diffsynth/models/sd_text_encoder.py
+diffsynth/models/siglip2_image_encoder.py
+diffsynth/models/step1x_connector.py
+diffsynth/models/step1x_text_encoder.py
+diffsynth/models/wan_video_animate_adapter.py
+diffsynth/models/wan_video_camera_controller.py
+diffsynth/models/wan_video_dit.py
+diffsynth/models/wan_video_dit_s2v.py
+diffsynth/models/wan_video_image_encoder.py
+diffsynth/models/wan_video_mot.py
+diffsynth/models/wan_video_motion_controller.py
+diffsynth/models/wan_video_text_encoder.py
+diffsynth/models/wan_video_vace.py
+diffsynth/models/wan_video_vae.py
+diffsynth/models/wav2vec.py
+diffsynth/models/z_image_controlnet.py
+diffsynth/models/z_image_dit.py
+diffsynth/models/z_image_image2lora.py
+diffsynth/models/z_image_text_encoder.py
+diffsynth/pipelines/flux2_image.py
+diffsynth/pipelines/flux_image.py
+diffsynth/pipelines/qwen_image.py
+diffsynth/pipelines/wan_video.py
+diffsynth/pipelines/z_image.py
+diffsynth/utils/controlnet/__init__.py
+diffsynth/utils/controlnet/annotator.py
+diffsynth/utils/controlnet/controlnet_input.py
+diffsynth/utils/data/__init__.py
+diffsynth/utils/lora/__init__.py
+diffsynth/utils/lora/flux.py
+diffsynth/utils/lora/general.py
+diffsynth/utils/lora/merge.py
+diffsynth/utils/lora/reset_rank.py
+diffsynth/utils/state_dict_converters/__init__.py
+diffsynth/utils/state_dict_converters/flux2_text_encoder.py
+diffsynth/utils/state_dict_converters/flux_controlnet.py
+diffsynth/utils/state_dict_converters/flux_dit.py
+diffsynth/utils/state_dict_converters/flux_infiniteyou.py
+diffsynth/utils/state_dict_converters/flux_ipadapter.py
+diffsynth/utils/state_dict_converters/flux_text_encoder_clip.py
+diffsynth/utils/state_dict_converters/flux_text_encoder_t5.py
+diffsynth/utils/state_dict_converters/flux_vae.py
+diffsynth/utils/state_dict_converters/nexus_gen.py
+diffsynth/utils/state_dict_converters/nexus_gen_projector.py
+diffsynth/utils/state_dict_converters/qwen_image_text_encoder.py
+diffsynth/utils/state_dict_converters/step1x_connector.py
+diffsynth/utils/state_dict_converters/wan_video_animate_adapter.py
+diffsynth/utils/state_dict_converters/wan_video_dit.py
+diffsynth/utils/state_dict_converters/wan_video_image_encoder.py
+diffsynth/utils/state_dict_converters/wan_video_mot.py
+diffsynth/utils/state_dict_converters/wan_video_vace.py
+diffsynth/utils/state_dict_converters/wan_video_vae.py
+diffsynth/utils/state_dict_converters/wans2v_audio_encoder.py
+diffsynth/utils/state_dict_converters/z_image_text_encoder.py
+diffsynth/utils/xfuser/__init__.py
+diffsynth/utils/xfuser/xdit_context_parallel.py

{diffsynth-2.0.3 → diffsynth-2.0.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "diffsynth"
-version = "2.0.3"
+version = "2.0.4"
 description = "Enjoy the magic of Diffusion models!"
 authors = [{name = "ModelScope Team"}]
 license = {text = "Apache-2.0"}

diffsynth-2.0.3/data/style/move.py

@@ -1,13 +0,0 @@
-from shutil import copy
-import os
-
-
-for i, style_id in enumerate([1, 2, 4, 5, 7, 8, 9]):
-    os.makedirs(f"/mnt/nas1/duanzhongjie.dzj/dev6_zimagebase/Z-Image-Omni-Base-i2L/assets/style/{i}", exist_ok=True)
-    for file_name in os.listdir(f"data/style/{style_id}"):
-        copy(f"data/style/{style_id}/{file_name}", f"/mnt/nas1/duanzhongjie.dzj/dev6_zimagebase/Z-Image-Omni-Base-i2L/assets/style/{i}/{file_name}")
-    image_id = 0
-    for file_name in sorted(os.listdir(f"data/style_out/1")):
-        if file_name.startswith(f"image_lora_{style_id}_"):
-            copy(f"data/style_out/1/{file_name}", f"/mnt/nas1/duanzhongjie.dzj/dev6_zimagebase/Z-Image-Omni-Base-i2L/assets/style/{i}/image_{image_id}.jpg")
-            image_id += 1

diffsynth-2.0.3/data/style/test.py

@@ -1,57 +0,0 @@
-from diffsynth.pipelines.z_image import (
-    ZImagePipeline, ModelConfig,
-    ZImageUnit_Image2LoRAEncode, ZImageUnit_Image2LoRADecode
-)
-from modelscope import snapshot_download
-from safetensors.torch import save_file
-import torch, os
-from PIL import Image
-
-# Use `vram_config` to enable LoRA hot-loading
-vram_config = {
-    "offload_dtype": torch.bfloat16,
-    "offload_device": "cuda",
-    "onload_dtype": torch.bfloat16,
-    "onload_device": "cuda",
-    "preparing_dtype": torch.bfloat16,
-    "preparing_device": "cuda",
-    "computation_dtype": torch.bfloat16,
-    "computation_device": "cuda",
-}
-
-# Load models
-pipe = ZImagePipeline.from_pretrained(
-    torch_dtype=torch.bfloat16,
-    device="cuda",
-    model_configs=[
-        ModelConfig(model_id="Tongyi-MAI/Z-Image-Omni-Base", origin_file_pattern="transformer/*.safetensors", **vram_config),
-        ModelConfig(model_id="Tongyi-MAI/Z-Image-Omni-Base", origin_file_pattern="siglip/model.safetensors"),
-        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors"),
-        ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
-        ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="SigLIP2-G384/model.safetensors"),
-        ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="DINOv3-7B/model.safetensors"),
-        ModelConfig("/mnt/nas1/duanzhongjie.dzj/dev3_zi2L/DiffSynth-Studio/models/train/ema_v30_0.9_0108.safetensors"),
-    ],
-    tokenizer_config=ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="tokenizer/"),
-)
-
-
-from diffsynth.core.data.operators import ImageCropAndResize
-processor_highres = ImageCropAndResize(height=1024, width=1024)
-for style_id in range(3, 12):
-    images = [Image.open(f"/mnt/nas1/duanzhongjie.dzj/dev3_zi2L/DiffSynth-Studio/data/style/{style_id}/{i}") for i in os.listdir(f"/mnt/nas1/duanzhongjie.dzj/dev3_zi2L/DiffSynth-Studio/data/style/{style_id}")]
-    os.makedirs(f"data/style/{style_id}", exist_ok=True)
-    for image_id, image in enumerate(images):
-        image = processor_highres(image)
-        image.save(f"data/style/{style_id}/{image_id}.jpg")
-    images = [Image.open(f"data/style/{style_id}/{i}.jpg") for i in range(len(images))]
-
-    with torch.no_grad():
-        embs = ZImageUnit_Image2LoRAEncode().process(pipe, image2lora_images=images)
-        lora = ZImageUnit_Image2LoRADecode().process(pipe, **embs)["lora"]
-
-    prompts = ["a cat", "a dog", "a girl"]
-    for prompt_id, prompt in enumerate(prompts):
-        negative_prompt = "泛黄，发绿，模糊，低分辨率，低质量图像，扭曲的肢体，诡异的外观，丑陋，AI感，噪点，网格感，JPEG压缩条纹，异常的肢体，水印，乱码，意义不明的字符"
-        image = pipe(prompt=prompt, negative_prompt=negative_prompt, seed=0, cfg_scale=7, num_inference_steps=50, positive_only_lora=lora, sigma_shift=8)
-        image.save(f"data/style_out/1/image_lora_{style_id}_{prompt_id}.jpg")