Skip to content

changed channel parameters for UNET and VAE. Changed configs parameters of CLIPText #5370

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 5 commits into from
Oct 17, 2023
Merged

changed channel parameters for UNET and VAE. Changed configs parameters of CLIPText #5370

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
d6889e3
changed channel parameters for UNET and VAE. Decreased hidden layers …
arkajyotimitra Oct 12, 2023
7d5c8b6
Merge branch 'main' of https://github.com/huggingface/diffusers into …
arkajyotimitra Oct 14, 2023
47ffc31
changed the assertion check range
arkajyotimitra Oct 14, 2023
dc4e1e7
Merge branch 'main' into fresh-fix
arkajyotimitra Oct 17, 2023
b64d8b6
clean up
DN6 Oct 17, 2023
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
33 changes: 18 additions & 15 deletions tests/pipelines/stable_diffusion/test_stable_diffusion.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,6 +82,7 @@ def _test_stable_diffusion_compile(in_queue, out_queue, timeout):

assert image.shape == (1, 512, 512, 3)
expected_slice = np.array([0.38019, 0.28647, 0.27321, 0.40377, 0.38290, 0.35446, 0.39218, 0.38165, 0.42239])

assert np.abs(image_slice - expected_slice).max() < 5e-3
except Exception:
error = f"{traceback.format_exc()}"
Expand All @@ -103,14 +104,15 @@ class StableDiffusionPipelineFastTests(
def get_dummy_components(self):
torch.manual_seed(0)
unet = UNet2DConditionModel(
block_out_channels=(32, 64),
layers_per_block=2,
block_out_channels=(4, 8),
layers_per_block=1,
sample_size=32,
in_channels=4,
out_channels=4,
down_block_types=("DownBlock2D", "CrossAttnDownBlock2D"),
up_block_types=("CrossAttnUpBlock2D", "UpBlock2D"),
cross_attention_dim=32,
norm_num_groups=2,
)
scheduler = DDIMScheduler(
beta_start=0.00085,
Expand All @@ -121,22 +123,23 @@ def get_dummy_components(self):
)
torch.manual_seed(0)
vae = AutoencoderKL(
block_out_channels=[32, 64],
block_out_channels=[4, 8],
in_channels=3,
out_channels=3,
down_block_types=["DownEncoderBlock2D", "DownEncoderBlock2D"],
up_block_types=["UpDecoderBlock2D", "UpDecoderBlock2D"],
latent_channels=4,
norm_num_groups=2,
)
torch.manual_seed(0)
text_encoder_config = CLIPTextConfig(
bos_token_id=0,
eos_token_id=2,
hidden_size=32,
intermediate_size=37,
intermediate_size=64,
layer_norm_eps=1e-05,
num_attention_heads=4,
num_hidden_layers=5,
num_attention_heads=8,
num_hidden_layers=3,
pad_token_id=1,
vocab_size=1000,
)
Expand Down Expand Up @@ -183,7 +186,7 @@ def test_stable_diffusion_ddim(self):
image_slice = image[0, -3:, -3:, -1]

assert image.shape == (1, 64, 64, 3)
expected_slice = np.array([0.5756, 0.6118, 0.5005, 0.5041, 0.5471, 0.4726, 0.4976, 0.4865, 0.4864])
expected_slice = np.array([0.3203, 0.4555, 0.4711, 0.3505, 0.3973, 0.4650, 0.5137, 0.3392, 0.4045])

assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

Expand Down Expand Up @@ -317,7 +320,7 @@ def test_stable_diffusion_ddim_factor_8(self):
image_slice = image[0, -3:, -3:, -1]

assert image.shape == (1, 136, 136, 3)
expected_slice = np.array([0.5524, 0.5626, 0.6069, 0.4727, 0.386, 0.3995, 0.4613, 0.4328, 0.4269])
expected_slice = np.array([0.4346, 0.5621, 0.5016, 0.3926, 0.4533, 0.4134, 0.5625, 0.5632, 0.5265])

assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

Expand All @@ -335,7 +338,7 @@ def test_stable_diffusion_pndm(self):
image_slice = image[0, -3:, -3:, -1]

assert image.shape == (1, 64, 64, 3)
expected_slice = np.array([0.5122, 0.5712, 0.4825, 0.5053, 0.5646, 0.4769, 0.5179, 0.4894, 0.4994])
expected_slice = np.array([0.3411, 0.5032, 0.4704, 0.3135, 0.4323, 0.4740, 0.5150, 0.3498, 0.4022])

assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

Expand Down Expand Up @@ -375,7 +378,7 @@ def test_stable_diffusion_k_lms(self):
image_slice = image[0, -3:, -3:, -1]

assert image.shape == (1, 64, 64, 3)
expected_slice = np.array([0.4873, 0.5443, 0.4845, 0.5004, 0.5549, 0.4850, 0.5191, 0.4941, 0.5065])
expected_slice = np.array([0.3149, 0.5246, 0.4796, 0.3218, 0.4469, 0.4729, 0.5151, 0.3597, 0.3954])

assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

Expand All @@ -394,7 +397,7 @@ def test_stable_diffusion_k_euler_ancestral(self):
image_slice = image[0, -3:, -3:, -1]

assert image.shape == (1, 64, 64, 3)
expected_slice = np.array([0.4872, 0.5444, 0.4846, 0.5003, 0.5549, 0.4850, 0.5189, 0.4941, 0.5067])
expected_slice = np.array([0.3151, 0.5243, 0.4794, 0.3217, 0.4468, 0.4728, 0.5152, 0.3598, 0.3954])

assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

Expand All @@ -413,7 +416,7 @@ def test_stable_diffusion_k_euler(self):
image_slice = image[0, -3:, -3:, -1]

assert image.shape == (1, 64, 64, 3)
expected_slice = np.array([0.4873, 0.5443, 0.4845, 0.5004, 0.5549, 0.4850, 0.5191, 0.4941, 0.5065])
expected_slice = np.array([0.3149, 0.5246, 0.4796, 0.3218, 0.4469, 0.4729, 0.5151, 0.3597, 0.3954])

assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

Expand Down Expand Up @@ -485,7 +488,7 @@ def test_stable_diffusion_negative_prompt(self):
image_slice = image[0, -3:, -3:, -1]

assert image.shape == (1, 64, 64, 3)
expected_slice = np.array([0.5114, 0.5706, 0.4772, 0.5028, 0.5637, 0.4732, 0.5169, 0.4881, 0.4977])
expected_slice = np.array([0.3458, 0.5120, 0.4800, 0.3116, 0.4348, 0.4802, 0.5237, 0.3467, 0.3991])

assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2

Expand Down Expand Up @@ -638,7 +641,7 @@ def test_stable_diffusion_1_1_pndm(self):
image_slice = image[0, -3:, -3:, -1].flatten()

assert image.shape == (1, 512, 512, 3)
expected_slice = np.array([0.43625, 0.43554, 0.36670, 0.40660, 0.39703, 0.38658, 0.43936, 0.43557, 0.40592])
expected_slice = np.array([0.3149, 0.5246, 0.4796, 0.3218, 0.4469, 0.4729, 0.5151, 0.3597, 0.3954])
assert np.abs(image_slice - expected_slice).max() < 3e-3

def test_stable_diffusion_v1_4_with_freeu(self):
Expand All @@ -665,7 +668,7 @@ def test_stable_diffusion_1_4_pndm(self):
image_slice = image[0, -3:, -3:, -1].flatten()

assert image.shape == (1, 512, 512, 3)
expected_slice = np.array([0.57400, 0.47841, 0.31625, 0.63583, 0.58306, 0.55056, 0.50825, 0.56306, 0.55748])
expected_slice = np.array([0.3458, 0.5120, 0.4800, 0.3116, 0.4348, 0.4802, 0.5237, 0.3467, 0.3991])
assert np.abs(image_slice - expected_slice).max() < 3e-3

def test_stable_diffusion_ddim(self):
Expand Down