Skip to content

config fixes #3060

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 11, 2023
Merged

config fixes #3060

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion examples/community/sd_text2img_k_diffusion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,7 @@ def __init__(
)

model = ModelWrapper(unet, scheduler.alphas_cumprod)
if scheduler.prediction_type == "v_prediction":
if scheduler.config.prediction_type == "v_prediction":
self.k_diffusion_model = CompVisVDenoiser(model)
else:
self.k_diffusion_model = CompVisDenoiser(model)
Expand Down
6 changes: 3 additions & 3 deletions src/diffusers/pipelines/audio_diffusion/pipeline_audio_diffusion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,9 +60,9 @@ def get_input_dims(self) -> Tuple:
input_module = self.vqvae if self.vqvae is not None else self.unet
# For backwards compatibility
sample_size = (
(input_module.sample_size, input_module.sample_size)
if type(input_module.sample_size) == int
else input_module.sample_size
(input_module.config.sample_size, input_module.config.sample_size)
if type(input_module.config.sample_size) == int
else input_module.config.sample_size
)
return sample_size

Expand Down
2 changes: 1 addition & 1 deletion src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_k_diffusion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,7 +113,7 @@ def __init__(
self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)

model = ModelWrapper(unet, scheduler.alphas_cumprod)
if scheduler.prediction_type == "v_prediction":
if scheduler.config.prediction_type == "v_prediction":
self.k_diffusion_model = CompVisVDenoiser(model)
else:
self.k_diffusion_model = CompVisDenoiser(model)
Expand Down
17 changes: 10 additions & 7 deletions tests/pipelines/audio_diffusion/test_audio_diffusion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,8 +115,11 @@ def test_audio_diffusion(self):
output = pipe(generator=generator, steps=4, return_dict=False)
image_from_tuple = output[0][0]

assert audio.shape == (1, (self.dummy_unet.sample_size[1] - 1) * mel.hop_length)
assert image.height == self.dummy_unet.sample_size[0] and image.width == self.dummy_unet.sample_size[1]
assert audio.shape == (1, (self.dummy_unet.config.sample_size[1] - 1) * mel.hop_length)
assert (
image.height == self.dummy_unet.config.sample_size[0]
and image.width == self.dummy_unet.config.sample_size[1]
)
image_slice = np.frombuffer(image.tobytes(), dtype="uint8")[:10]
image_from_tuple_slice = np.frombuffer(image_from_tuple.tobytes(), dtype="uint8")[:10]
expected_slice = np.array([69, 255, 255, 255, 0, 0, 77, 181, 12, 127])
Expand All @@ -133,14 +136,14 @@ def test_audio_diffusion(self):
pipe.set_progress_bar_config(disable=None)

np.random.seed(0)
raw_audio = np.random.uniform(-1, 1, ((dummy_vqvae_and_unet[0].sample_size[1] - 1) * mel.hop_length,))
raw_audio = np.random.uniform(-1, 1, ((dummy_vqvae_and_unet[0].config.sample_size[1] - 1) * mel.hop_length,))
generator = torch.Generator(device=device).manual_seed(42)
output = pipe(raw_audio=raw_audio, generator=generator, start_step=5, steps=10)
image = output.images[0]

assert (
image.height == self.dummy_vqvae_and_unet[0].sample_size[0]
and image.width == self.dummy_vqvae_and_unet[0].sample_size[1]
image.height == self.dummy_vqvae_and_unet[0].config.sample_size[0]
and image.width == self.dummy_vqvae_and_unet[0].config.sample_size[1]
)
image_slice = np.frombuffer(image.tobytes(), dtype="uint8")[:10]
expected_slice = np.array([120, 117, 110, 109, 138, 167, 138, 148, 132, 121])
Expand Down Expand Up @@ -183,8 +186,8 @@ def test_audio_diffusion(self):
audio = output.audios[0]
image = output.images[0]

assert audio.shape == (1, (pipe.unet.sample_size[1] - 1) * pipe.mel.hop_length)
assert image.height == pipe.unet.sample_size[0] and image.width == pipe.unet.sample_size[1]
assert audio.shape == (1, (pipe.unet.config.sample_size[1] - 1) * pipe.mel.hop_length)
assert image.height == pipe.unet.config.sample_size[0] and image.width == pipe.unet.config.sample_size[1]
image_slice = np.frombuffer(image.tobytes(), dtype="uint8")[:10]
expected_slice = np.array([151, 167, 154, 144, 122, 134, 121, 105, 70, 26])

Expand Down