File size: 2,880 Bytes
903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 9ed958c 903e660 | 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 | import torch
from diffusers import ModelMixin, SchedulerMixin
from diffusers.modular_pipelines.modular_pipeline_utils import ComponentSpec, InputParam, OutputParam
from diffusers.utils.torch_utils import randn_tensor
from .operations import ResolvableBlock
class KimodoLatentsStep(ResolvableBlock):
model_name = "kimodo"
@property
def description(self):
return "Draw the initial motion-feature noise for an explicit frame count."
@property
def expected_components(self):
return self.resolve([ComponentSpec("transformer", ModelMixin)])
@property
def inputs(self):
return [
InputParam(
"num_frames", type_hint=int, default=120, description="Motion samples at the model frame rate."
),
InputParam(
"seed",
type_hint=int,
default=42,
description="Seed for a generator on the execution device; ignored when `generator` is given.",
),
InputParam.template("generator"),
]
@property
def intermediate_outputs(self):
return [
OutputParam("latents", type_hint=torch.Tensor, description="Noisy motion features, (1, frames, features).")
]
def __call__(self, components, state):
block = self.get_block_state(state)
if block.num_frames < 2:
raise ValueError("Motion requires at least two frames")
device = components._execution_device
generator = block.generator
if generator is None:
generator = torch.Generator(device=device).manual_seed(block.seed)
transformer = components.transformer
block.latents = randn_tensor(
(1, block.num_frames, transformer.motion_rep_dim),
generator=generator,
device=device,
dtype=transformer.dtype,
)
self.set_block_state(state, block)
return components, state
class KimodoTimestepsStep(ResolvableBlock):
model_name = "kimodo"
@property
def description(self):
return "Set the Kimodo DDIM schedule for this run."
@property
def expected_components(self):
return self.resolve([ComponentSpec("scheduler", SchedulerMixin)])
@property
def inputs(self):
return [InputParam.template("num_inference_steps", default=100)]
@property
def intermediate_outputs(self):
return [OutputParam("timesteps", type_hint=torch.Tensor, description="Descending training-step indices.")]
def __call__(self, components, state):
block = self.get_block_state(state)
components.scheduler.set_timesteps(block.num_inference_steps, device=components._execution_device)
block.timesteps = components.scheduler.timesteps
self.set_block_state(state, block)
return components, state
|