add webui

diffsynth/models/dinov3_image_encoder.py

@@ -1,4 +1,4 @@
-from transformers import DINOv3ViTModel, DINOv3ViTImageProcessorFast
+from transformers import DINOv3ViTModel, DINOv3ViTImageProcessor
 from transformers.models.dinov3_vit.modeling_dinov3_vit import DINOv3ViTConfig
 import torch
 
@@ -40,7 +40,7 @@ class DINOv3ImageEncoder(DINOv3ViTModel):
             value_bias = False
         )
         super().__init__(config)
-        self.processor = DINOv3ViTImageProcessorFast(
+        self.processor = DINOv3ViTImageProcessor(
             crop_size = None,
             data_format = "channels_first",
             default_to_square = True,
@@ -56,7 +56,7 @@ class DINOv3ImageEncoder(DINOv3ViTModel):
                 0.456,
                 0.406
             ],
-            image_processor_type = "DINOv3ViTImageProcessorFast",
+            image_processor_type = "DINOv3ViTImageProcessor",
             image_std = [
                 0.229,
                 0.224,

diffsynth/models/siglip2_image_encoder.py

@@ -1,5 +1,5 @@
 from transformers.models.siglip.modeling_siglip import SiglipVisionTransformer, SiglipVisionConfig
-from transformers import SiglipImageProcessor, Siglip2VisionModel, Siglip2VisionConfig, Siglip2ImageProcessorFast
+from transformers import SiglipImageProcessor, Siglip2VisionModel, Siglip2VisionConfig, Siglip2ImageProcessor
 import torch
 
 from diffsynth.core.device.npu_compatible_device import get_device_type
@@ -90,7 +90,7 @@ class Siglip2ImageEncoder428M(Siglip2VisionModel):
             transformers_version = "4.57.1"
         )
         super().__init__(config)
-        self.processor = Siglip2ImageProcessorFast(
+        self.processor = Siglip2ImageProcessor(
             **{
                 "data_format": "channels_first",
                 "default_to_square": True,
@@ -106,7 +106,7 @@ class Siglip2ImageEncoder428M(Siglip2VisionModel):
                     0.5,
                     0.5
                 ],
-                "image_processor_type": "Siglip2ImageProcessorFast",
+                "image_processor_type": "Siglip2ImageProcessor",
                 "image_std": [
                     0.5,
                     0.5,

diffsynth/pipelines/z_image.py

@@ -95,7 +95,7 @@ class ZImagePipeline(BasePipeline):
     def __call__(
         self,
         # Prompt
-        prompt: str,
+        prompt: str = "",
         negative_prompt: str = "",
         cfg_scale: float = 1.0,
         # Image
@@ -109,7 +109,7 @@ class ZImagePipeline(BasePipeline):
         width: int = 1024,
         # Randomness
         seed: int = None,
-        rand_device: str = "cpu",
+        rand_device: Union[str, torch.device] = "cpu",
         # Steps
         num_inference_steps: int = 8,
         sigma_shift: float = None,