mirror of
https://github.com/huggingface/diffusers.git
synced 2026-10-24 20:59:27 +03:00
6184688f71
* add a modular test that pins the canonical latents form each family leaves in the state * move unpack out of the flux, krea2 and ltx decoders into the core denoise groups * pop the unpack step from a copy of the blocks in the deprecation tests * let families that decode inside the denoise loop opt out of the latents-form test * document the canonical latents form in the modular reference * [docs] canonical latents form: name normalize, patchify and pack separately Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> * require geometry on the unpack steps and test the deprecated decode path directly * skip the canonical latents test explicitly for ltx 2.5 too * remove the packed latents path in 0.47.0, five releases after 0.42 * update the latents_output_name comment for the explicit skips * move the packed test latents to the test device --------- Co-authored-by: YiYi Xu <yixu310@gmail.com> Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
66 lines
2.2 KiB
Python
66 lines
2.2 KiB
Python
# coding=utf-8
|
|
# Copyright 2026 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 torch
|
|
|
|
from diffusers.modular_pipelines import EchoBlocks, EchoModularPipeline
|
|
|
|
from ..testing_utils import BaseModularPipelineTesterConfig
|
|
|
|
|
|
class EchoModularPipelineTesterConfig(BaseModularPipelineTesterConfig):
|
|
pipeline_class = EchoModularPipeline
|
|
pipeline_blocks_class = EchoBlocks
|
|
pretrained_model_name_or_path = "Echo-Team/tiny-echo-modular-pipe"
|
|
expected_latents_shape = (1, 4, 3, 16, 16)
|
|
params = frozenset(
|
|
[
|
|
"prompt",
|
|
"image",
|
|
"memory_images",
|
|
"memory_audio_waveforms",
|
|
"height",
|
|
"width",
|
|
"num_frames",
|
|
"frame_rate",
|
|
"model_frame_rate",
|
|
"sigmas",
|
|
]
|
|
)
|
|
batch_params = frozenset(["prompt"])
|
|
optional_params = frozenset(["num_videos_per_prompt", "latents", "audio_latents", "output_type"])
|
|
not_params = frozenset(["negative_prompt", "guidance_scale", "num_inference_steps"])
|
|
expected_workflow_blocks = {}
|
|
output_name = "videos"
|
|
|
|
def get_dummy_inputs(self, seed=0):
|
|
generator = self.get_generator(seed)
|
|
return {
|
|
"prompt": "a robot dancing",
|
|
"image": torch.rand((1, 3, 32, 32), generator=generator),
|
|
"memory_images": [
|
|
torch.rand((1, 3, 32, 32), generator=generator),
|
|
torch.rand((1, 3, 32, 32), generator=generator),
|
|
],
|
|
"generator": self.get_generator(seed),
|
|
"sigmas": [1.0, 0.0],
|
|
"height": 32,
|
|
"width": 32,
|
|
"num_frames": 5,
|
|
"frame_rate": 25.0,
|
|
"max_sequence_length": 16,
|
|
"output_type": "pt",
|
|
}
|