Fix config prints and save, load of pipelines (#2849)

* [Config] Fix config prints and save, load

* Only use potential nn.Modules for dtype and device

* Correct vae image processor

* make sure in_channels is not accessed directly

* make sure in channels is only accessed via config

* Make sure schedulers only access config attributes

* Make sure to access config in SAG

* Fix vae processor and make style

* add tests

* uP

* make style

* Fix more naming issues

* Final fix with vae config

* change more

Author: patrickvonplaten

docs/source/en/tutorials/basic_training.mdx

@@ -344,7 +344,7 @@ Now you can wrap all these components together in a training loop with 🤗 Acce
 
 ...             # Sample a random timestep for each image
 ...             timesteps = torch.randint(
-...                 0, noise_scheduler.num_train_timesteps, (bs,), device=clean_images.device
+...                 0, noise_scheduler.config.num_train_timesteps, (bs,), device=clean_images.device
 ...             ).long()
 
 ...             # Add noise to the clean images according to the noise magnitude at each timestep

docs/source/en/using-diffusers/contribute_pipeline.mdx

@@ -62,7 +62,7 @@ class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
 
     def __call__(self):
         image = torch.randn(
-            (1, self.unet.in_channels, self.unet.sample_size, self.unet.sample_size),
+            (1, self.unet.config.in_channels, self.unet.config.sample_size, self.unet.config.sample_size),
         )
         timestep = 1
 
@@ -108,7 +108,7 @@ class UnetSchedulerOneForwardPipeline(DiffusionPipeline):
 
     def __call__(self):
         image = torch.randn(
-            (1, self.unet.in_channels, self.unet.sample_size, self.unet.sample_size),
+            (1, self.unet.config.in_channels, self.unet.config.sample_size, self.unet.config.sample_size),
         )
         timestep = 1
 

docs/source/en/using-diffusers/custom_pipeline_overview.mdx

@@ -89,7 +89,9 @@ class MyPipeline(DiffusionPipeline):
     @torch.no_grad()
     def __call__(self, batch_size: int = 1, num_inference_steps: int = 50):
         # Sample gaussian noise to begin loop
-        image = torch.randn((batch_size, self.unet.in_channels, self.unet.sample_size, self.unet.sample_size))
+        image = torch.randn(
+            (batch_size, self.unet.config.in_channels, self.unet.config.sample_size, self.unet.config.sample_size)
+        )
 
         image = image.to(self.device)
 

examples/community/bit_diffusion.py

@@ -238,7 +238,7 @@ def __call__(
         **kwargs,
     ) -> Union[Tuple, ImagePipelineOutput]:
         latents = torch.randn(
-            (batch_size, self.unet.in_channels, height, width),
+            (batch_size, self.unet.config.in_channels, height, width),
             generator=generator,
         )
         latents = decimal_to_bits(latents) * self.bit_scale

examples/community/clip_guided_stable_diffusion.py

@@ -254,7 +254,7 @@ def __call__(
         # Unlike in other pipelines, latents need to be generated in the target device
         # for 1-to-1 results reproducibility with the CompVis implementation.
         # However this currently doesn't work in `mps`.
-        latents_shape = (batch_size * num_images_per_prompt, self.unet.in_channels, height // 8, width // 8)
+        latents_shape = (batch_size * num_images_per_prompt, self.unet.config.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
         if latents is None:
             if self.device.type == "mps":

examples/community/clip_guided_stable_diffusion_img2img.py

@@ -414,7 +414,7 @@ def __call__(
         # Unlike in other pipelines, latents need to be generated in the target device
         # for 1-to-1 results reproducibility with the CompVis implementation.
         # However this currently doesn't work in `mps`.
-        latents_shape = (batch_size * num_images_per_prompt, self.unet.in_channels, height // 8, width // 8)
+        latents_shape = (batch_size * num_images_per_prompt, self.unet.config.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
         if latents is None:
             if self.device.type == "mps":

examples/community/composable_stable_diffusion.py

@@ -513,7 +513,7 @@ def __call__(
         timesteps = self.scheduler.timesteps
 
         # 5. Prepare latent variables
-        num_channels_latents = self.unet.in_channels
+        num_channels_latents = self.unet.config.in_channels
         latents = self.prepare_latents(
             batch_size * num_images_per_prompt,
             num_channels_latents,

examples/community/imagic_stable_diffusion.py

@@ -424,7 +424,7 @@ def __call__(
         # Unlike in other pipelines, latents need to be generated in the target device
         # for 1-to-1 results reproducibility with the CompVis implementation.
         # However this currently doesn't work in `mps`.
-        latents_shape = (1, self.unet.in_channels, height // 8, width // 8)
+        latents_shape = (1, self.unet.config.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
         if self.device.type == "mps":
             # randn does not exist on mps

examples/community/interpolate_stable_diffusion.py

@@ -320,7 +320,7 @@ def __call__(
         # Unlike in other pipelines, latents need to be generated in the target device
         # for 1-to-1 results reproducibility with the CompVis implementation.
         # However this currently doesn't work in `mps`.
-        latents_shape = (batch_size * num_images_per_prompt, self.unet.in_channels, height // 8, width // 8)
+        latents_shape = (batch_size * num_images_per_prompt, self.unet.config.in_channels, height // 8, width // 8)
         latents_dtype = text_embeddings.dtype
         if latents is None:
             if self.device.type == "mps":
@@ -416,7 +416,7 @@ def embed_text(self, text):
     def get_noise(self, seed, dtype=torch.float32, height=512, width=512):
         """Takes in random seed and returns corresponding noise vector"""
         return torch.randn(
-            (1, self.unet.in_channels, height // 8, width // 8),
+            (1, self.unet.config.in_channels, height // 8, width // 8),
             generator=torch.Generator(device=self.device).manual_seed(seed),
             device=self.device,
             dtype=dtype,

examples/community/lpw_stable_diffusion.py

@@ -627,7 +627,7 @@ def prepare_latents(self, image, timestep, batch_size, height, width, dtype, dev
         if image is None:
             shape = (
                 batch_size,
-                self.unet.in_channels,
+                self.unet.config.in_channels,
                 height // self.vae_scale_factor,
                 width // self.vae_scale_factor,
             )