File size: 1,620 Bytes
c0af20c |
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 |
# 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 unittest
import torch
from diffusers import DDIMScheduler, TextToVideoZeroPipeline
from diffusers.utils import load_pt, require_torch_gpu, slow
from ..test_pipelines_common import assert_mean_pixel_difference
@slow
@require_torch_gpu
class TextToVideoZeroPipelineSlowTests(unittest.TestCase):
def test_full_model(self):
model_id = "runwayml/stable-diffusion-v1-5"
pipe = TextToVideoZeroPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
generator = torch.Generator(device="cuda").manual_seed(0)
prompt = "A bear is playing a guitar on Times Square"
result = pipe(prompt=prompt, generator=generator).images
expected_result = load_pt(
"https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/text-to-video/A bear is playing a guitar on Times Square.pt"
)
assert_mean_pixel_difference(result, expected_result)
|