diffusers 0.17.1__py3-none-any.whl → 0.18.2__py3-none-any.whl

diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py

@@ -24,7 +24,12 @@ from transformers import CLIPImageProcessor, CLIPTextModel, CLIPTokenizer
 from ...image_processor import VaeImageProcessor
 from ...loaders import LoraLoaderMixin, TextualInversionLoaderMixin
 from ...models import AutoencoderKL, UNet2DConditionModel
-from ...models.attention_processor import AttnProcessor2_0, LoRAXFormersAttnProcessor, XFormersAttnProcessor
+from ...models.attention_processor import (
+    AttnProcessor2_0,
+    LoRAAttnProcessor2_0,
+    LoRAXFormersAttnProcessor,
+    XFormersAttnProcessor,
+)
 from ...schedulers import DDPMScheduler, KarrasDiffusionSchedulers
 from ...utils import deprecate, is_accelerate_available, is_accelerate_version, logging, randn_tensor
 from ..pipeline_utils import DiffusionPipeline
@@ -743,14 +748,19 @@ class StableDiffusionUpscalePipeline(DiffusionPipeline, TextualInversionLoaderMi
         # make sure the VAE is in float32 mode, as it overflows in float16
         self.vae.to(dtype=torch.float32)
 
-        use_torch_2_0_or_xformers = self.vae.decoder.mid_block.attentions[0].processor in [
-            AttnProcessor2_0,
-            XFormersAttnProcessor,
-            LoRAXFormersAttnProcessor,
-        ]
+        use_torch_2_0_or_xformers = isinstance(
+            self.vae.decoder.mid_block.attentions[0].processor,
+            (
+                AttnProcessor2_0,
+                XFormersAttnProcessor,
+                LoRAXFormersAttnProcessor,
+                LoRAAttnProcessor2_0,
+            ),
+        )
+
         # if xformers or torch_2_0 is used attention block does not need
         # to be in float32 which can save lots of memory
-        if not use_torch_2_0_or_xformers:
+        if use_torch_2_0_or_xformers:
             self.vae.post_quant_conv.to(latents.dtype)
             self.vae.decoder.conv_in.to(latents.dtype)
             self.vae.decoder.mid_block.to(latents.dtype)

diffusers/pipelines/stable_diffusion_xl/__init__.py

@@ -0,0 +1,26 @@
+from dataclasses import dataclass
+from typing import List, Optional, Union
+
+import numpy as np
+import PIL
+
+from ...utils import BaseOutput, is_invisible_watermark_available, is_torch_available, is_transformers_available
+
+
+@dataclass
+class StableDiffusionXLPipelineOutput(BaseOutput):
+    """
+    Output class for Stable Diffusion pipelines.
+
+    Args:
+        images (`List[PIL.Image.Image]` or `np.ndarray`)
+            List of denoised PIL images of length `batch_size` or numpy array of shape `(batch_size, height, width,
+            num_channels)`. PIL images or numpy array present the denoised images of the diffusion pipeline.
+    """
+
+    images: Union[List[PIL.Image.Image], np.ndarray]
+
+
+if is_transformers_available() and is_torch_available() and is_invisible_watermark_available():
+    from .pipeline_stable_diffusion_xl import StableDiffusionXLPipeline
+    from .pipeline_stable_diffusion_xl_img2img import StableDiffusionXLImg2ImgPipeline