File size: 2,454 Bytes
43b7e92 |
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 |
# 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 torch
from diffusers import SD3Transformer2DModel
from diffusers.utils.testing_utils import (
enable_full_determinism,
torch_device,
)
from ..test_modeling_common import ModelTesterMixin
enable_full_determinism()
class SD3TransformerTests(ModelTesterMixin, unittest.TestCase):
model_class = SD3Transformer2DModel
main_input_name = "hidden_states"
@property
def dummy_input(self):
batch_size = 2
num_channels = 4
height = width = embedding_dim = 32
pooled_embedding_dim = embedding_dim * 2
sequence_length = 154
hidden_states = torch.randn((batch_size, num_channels, height, width)).to(torch_device)
encoder_hidden_states = torch.randn((batch_size, sequence_length, embedding_dim)).to(torch_device)
pooled_prompt_embeds = torch.randn((batch_size, pooled_embedding_dim)).to(torch_device)
timestep = torch.randint(0, 1000, size=(batch_size,)).to(torch_device)
return {
"hidden_states": hidden_states,
"encoder_hidden_states": encoder_hidden_states,
"pooled_projections": pooled_prompt_embeds,
"timestep": timestep,
}
@property
def input_shape(self):
return (4, 32, 32)
@property
def output_shape(self):
return (4, 32, 32)
def prepare_init_args_and_inputs_for_common(self):
init_dict = {
"sample_size": 32,
"patch_size": 1,
"in_channels": 4,
"num_layers": 1,
"attention_head_dim": 8,
"num_attention_heads": 4,
"caption_projection_dim": 32,
"joint_attention_dim": 32,
"pooled_projection_dim": 64,
"out_channels": 4,
}
inputs_dict = self.dummy_input
return init_dict, inputs_dict
|