File size: 3,352 Bytes
8206b09
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# coding=utf-8
# Copyright 2023 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 random
import unittest

import torch

from diffusers import IFImg2ImgSuperResolutionPipeline
from diffusers.utils import floats_tensor
from diffusers.utils.import_utils import is_xformers_available
from diffusers.utils.testing_utils import skip_mps, torch_device

from ..pipeline_params import TEXT_GUIDED_IMAGE_VARIATION_BATCH_PARAMS, TEXT_GUIDED_IMAGE_VARIATION_PARAMS
from ..test_pipelines_common import PipelineTesterMixin
from . import IFPipelineTesterMixin


@skip_mps
class IFImg2ImgSuperResolutionPipelineFastTests(PipelineTesterMixin, IFPipelineTesterMixin, unittest.TestCase):
    pipeline_class = IFImg2ImgSuperResolutionPipeline
    params = TEXT_GUIDED_IMAGE_VARIATION_PARAMS - {"width", "height"}
    batch_params = TEXT_GUIDED_IMAGE_VARIATION_BATCH_PARAMS.union({"original_image"})
    required_optional_params = PipelineTesterMixin.required_optional_params - {"latents"}

    def get_dummy_components(self):
        return self._get_superresolution_dummy_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)

        original_image = floats_tensor((1, 3, 32, 32), rng=random.Random(seed)).to(device)
        image = floats_tensor((1, 3, 16, 16), rng=random.Random(seed)).to(device)

        inputs = {
            "prompt": "A painting of a squirrel eating a burger",
            "image": image,
            "original_image": original_image,
            "generator": generator,
            "num_inference_steps": 2,
            "output_type": "numpy",
        }

        return inputs

    @unittest.skipIf(
        torch_device != "cuda" or not is_xformers_available(),
        reason="XFormers attention is only available with CUDA and `xformers` installed",
    )
    def test_xformers_attention_forwardGenerator_pass(self):
        self._test_xformers_attention_forwardGenerator_pass(expected_max_diff=1e-3)

    def test_save_load_optional_components(self):
        self._test_save_load_optional_components()

    @unittest.skipIf(torch_device != "cuda", reason="float16 requires CUDA")
    def test_save_load_float16(self):
        # Due to non-determinism in save load of the hf-internal-testing/tiny-random-t5 text encoder
        super().test_save_load_float16(expected_max_diff=1e-1)

    def test_attention_slicing_forward_pass(self):
        self._test_attention_slicing_forward_pass(expected_max_diff=1e-2)

    def test_save_load_local(self):
        self._test_save_load_local()

    def test_inference_batch_single_identical(self):
        self._test_inference_batch_single_identical(
            expected_max_diff=1e-2,
        )