| # coding=utf-8 | |
| # Copyright 2025 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.models.transformers import TransformerTemporalModel | |
| from ...testing_utils import ( | |
| enable_full_determinism, | |
| torch_device, | |
| ) | |
| from ..test_modeling_common import ModelTesterMixin | |
| enable_full_determinism() | |
| class TemporalTransformerTests(ModelTesterMixin, unittest.TestCase): | |
| model_class = TransformerTemporalModel | |
| main_input_name = "hidden_states" | |
| def dummy_input(self): | |
| batch_size = 2 | |
| num_channels = 4 | |
| height = width = 32 | |
| hidden_states = torch.randn((batch_size, num_channels, height, width)).to(torch_device) | |
| timestep = torch.randint(0, 1000, size=(batch_size,)).to(torch_device) | |
| return { | |
| "hidden_states": hidden_states, | |
| "timestep": timestep, | |
| } | |
| def input_shape(self): | |
| return (4, 32, 32) | |
| def output_shape(self): | |
| return (4, 32, 32) | |
| def prepare_init_args_and_inputs_for_common(self): | |
| init_dict = { | |
| "num_attention_heads": 8, | |
| "attention_head_dim": 4, | |
| "in_channels": 4, | |
| "num_layers": 1, | |
| "norm_num_groups": 1, | |
| } | |
| inputs_dict = self.dummy_input | |
| return init_dict, inputs_dict | |