File size: 5,048 Bytes
dde5d93 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
# coding=utf-8
# Copyright 2024 HuggingFace Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import unittest
import numpy as np
import torch
from diffusers import (
AutoencoderKL,
EulerDiscreteScheduler,
KolorsPipeline,
UNet2DConditionModel,
)
from diffusers.pipelines.kolors import ChatGLMModel, ChatGLMTokenizer
from diffusers.utils.testing_utils import enable_full_determinism
from ..pipeline_params import (
TEXT_TO_IMAGE_BATCH_PARAMS,
TEXT_TO_IMAGE_CALLBACK_CFG_PARAMS,
TEXT_TO_IMAGE_IMAGE_PARAMS,
TEXT_TO_IMAGE_PARAMS,
)
from ..test_pipelines_common import PipelineTesterMixin
enable_full_determinism()
class KolorsPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
pipeline_class = KolorsPipeline
params = TEXT_TO_IMAGE_PARAMS
batch_params = TEXT_TO_IMAGE_BATCH_PARAMS
image_params = TEXT_TO_IMAGE_IMAGE_PARAMS
image_latents_params = TEXT_TO_IMAGE_IMAGE_PARAMS
callback_cfg_params = TEXT_TO_IMAGE_CALLBACK_CFG_PARAMS.union({"add_text_embeds", "add_time_ids"})
def get_dummy_components(self, time_cond_proj_dim=None):
torch.manual_seed(0)
unet = UNet2DConditionModel(
block_out_channels=(2, 4),
layers_per_block=2,
time_cond_proj_dim=time_cond_proj_dim,
sample_size=32,
in_channels=4,
out_channels=4,
down_block_types=("DownBlock2D", "CrossAttnDownBlock2D"),
up_block_types=("CrossAttnUpBlock2D", "UpBlock2D"),
# specific config below
attention_head_dim=(2, 4),
use_linear_projection=True,
addition_embed_type="text_time",
addition_time_embed_dim=8,
transformer_layers_per_block=(1, 2),
projection_class_embeddings_input_dim=56,
cross_attention_dim=8,
norm_num_groups=1,
)
scheduler = EulerDiscreteScheduler(
beta_start=0.00085,
beta_end=0.012,
steps_offset=1,
beta_schedule="scaled_linear",
timestep_spacing="leading",
)
torch.manual_seed(0)
vae = AutoencoderKL(
block_out_channels=[32, 64],
in_channels=3,
out_channels=3,
down_block_types=["DownEncoderBlock2D", "DownEncoderBlock2D"],
up_block_types=["UpDecoderBlock2D", "UpDecoderBlock2D"],
latent_channels=4,
sample_size=128,
)
torch.manual_seed(0)
text_encoder = ChatGLMModel.from_pretrained("hf-internal-testing/tiny-random-chatglm3-6b")
tokenizer = ChatGLMTokenizer.from_pretrained("hf-internal-testing/tiny-random-chatglm3-6b")
components = {
"unet": unet,
"scheduler": scheduler,
"vae": vae,
"text_encoder": text_encoder,
"tokenizer": tokenizer,
"image_encoder": None,
"feature_extractor": None,
}
return components
def get_dummy_inputs(self, device, seed=0):
if str(device).startswith("mps"):
generator = torch.manual_seed(seed)
else:
generator = torch.Generator(device=device).manual_seed(seed)
inputs = {
"prompt": "A painting of a squirrel eating a burger",
"generator": generator,
"num_inference_steps": 2,
"guidance_scale": 5.0,
"output_type": "np",
}
return inputs
def test_inference(self):
device = "cpu"
components = self.get_dummy_components()
pipe = self.pipeline_class(**components)
pipe.to(device)
pipe.set_progress_bar_config(disable=None)
inputs = self.get_dummy_inputs(device)
image = pipe(**inputs).images
image_slice = image[0, -3:, -3:, -1]
self.assertEqual(image.shape, (1, 64, 64, 3))
expected_slice = np.array(
[0.26413745, 0.4425478, 0.4102801, 0.42693347, 0.52529025, 0.3867405, 0.47512037, 0.41538602, 0.43855375]
)
max_diff = np.abs(image_slice.flatten() - expected_slice).max()
self.assertLessEqual(max_diff, 1e-3)
def test_save_load_optional_components(self):
super().test_save_load_optional_components(expected_max_difference=2e-4)
def test_save_load_float16(self):
super().test_save_load_float16(expected_max_diff=2e-1)
def test_inference_batch_single_identical(self):
self._test_inference_batch_single_identical(expected_max_diff=5e-4)
|