Spaces:
Running
on
Zero
Running
on
Zero
File size: 5,515 Bytes
22a452a |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 |
# 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 transformers import (
AutoTokenizer,
CLIPTextConfig,
CLIPTextModelWithProjection,
CLIPTokenizer,
LlamaForCausalLM,
T5EncoderModel,
)
from diffusers import (
AutoencoderKL,
FlowMatchEulerDiscreteScheduler,
HiDreamImagePipeline,
HiDreamImageTransformer2DModel,
)
from diffusers.utils.testing_utils import enable_full_determinism
from ..pipeline_params import TEXT_TO_IMAGE_BATCH_PARAMS, TEXT_TO_IMAGE_IMAGE_PARAMS, TEXT_TO_IMAGE_PARAMS
from ..test_pipelines_common import PipelineTesterMixin
enable_full_determinism()
class HiDreamImagePipelineFastTests(PipelineTesterMixin, unittest.TestCase):
pipeline_class = HiDreamImagePipeline
params = TEXT_TO_IMAGE_PARAMS - {"cross_attention_kwargs", "prompt_embeds", "negative_prompt_embeds"}
batch_params = TEXT_TO_IMAGE_BATCH_PARAMS
image_params = TEXT_TO_IMAGE_IMAGE_PARAMS
image_latents_params = TEXT_TO_IMAGE_IMAGE_PARAMS
required_optional_params = PipelineTesterMixin.required_optional_params
test_layerwise_casting = True
supports_dduf = False
def get_dummy_components(self):
torch.manual_seed(0)
transformer = HiDreamImageTransformer2DModel(
patch_size=2,
in_channels=4,
out_channels=4,
num_layers=1,
num_single_layers=1,
attention_head_dim=8,
num_attention_heads=4,
caption_channels=[32, 16],
text_emb_dim=64,
num_routed_experts=4,
num_activated_experts=2,
axes_dims_rope=(4, 2, 2),
max_resolution=(32, 32),
llama_layers=(0, 1),
).eval()
torch.manual_seed(0)
vae = AutoencoderKL(scaling_factor=0.3611, shift_factor=0.1159)
clip_text_encoder_config = CLIPTextConfig(
bos_token_id=0,
eos_token_id=2,
hidden_size=32,
intermediate_size=37,
layer_norm_eps=1e-05,
num_attention_heads=4,
num_hidden_layers=5,
pad_token_id=1,
vocab_size=1000,
hidden_act="gelu",
projection_dim=32,
max_position_embeddings=128,
)
torch.manual_seed(0)
text_encoder = CLIPTextModelWithProjection(clip_text_encoder_config)
torch.manual_seed(0)
text_encoder_2 = CLIPTextModelWithProjection(clip_text_encoder_config)
torch.manual_seed(0)
text_encoder_3 = T5EncoderModel.from_pretrained("hf-internal-testing/tiny-random-t5")
torch.manual_seed(0)
text_encoder_4 = LlamaForCausalLM.from_pretrained("hf-internal-testing/tiny-random-LlamaForCausalLM")
text_encoder_4.generation_config.pad_token_id = 1
tokenizer = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
tokenizer_2 = CLIPTokenizer.from_pretrained("hf-internal-testing/tiny-random-clip")
tokenizer_3 = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-t5")
tokenizer_4 = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-LlamaForCausalLM")
scheduler = FlowMatchEulerDiscreteScheduler()
components = {
"scheduler": scheduler,
"vae": vae,
"text_encoder": text_encoder,
"tokenizer": tokenizer,
"text_encoder_2": text_encoder_2,
"tokenizer_2": tokenizer_2,
"text_encoder_3": text_encoder_3,
"tokenizer_3": tokenizer_3,
"text_encoder_4": text_encoder_4,
"tokenizer_4": tokenizer_4,
"transformer": transformer,
}
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)[0]
generated_image = image[0]
self.assertEqual(generated_image.shape, (128, 128, 3))
expected_image = torch.randn(128, 128, 3).numpy()
max_diff = np.abs(generated_image - expected_image).max()
self.assertLessEqual(max_diff, 1e10)
def test_inference_batch_single_identical(self):
super().test_inference_batch_single_identical(expected_max_diff=3e-4)
|