Release V2.1.7 stable facade UI
This commit is contained in:
@@ -1,159 +1,53 @@
|
||||
from types import SimpleNamespace
|
||||
|
||||
import torch
|
||||
|
||||
from ComfyUI_H3_Continuum_Join.constants import (
|
||||
CONTINUUM_INTEROP_KEY,
|
||||
DIAGNOSTICS_BASIC,
|
||||
PROMPT_MODE_FIXED,
|
||||
V2_CONTINUITY_OPTIONS,
|
||||
)
|
||||
from ComfyUI_H3_Continuum_Join.constants import CONTINUUM_INTEROP_KEY, DIAGNOSTICS_BASIC, PROMPT_MODE_FIXED, V2_CONTINUITY_OPTIONS
|
||||
from ComfyUI_H3_Continuum_Join.temporal import audio_latent_t, video_latent_t
|
||||
from ComfyUI_H3_Continuum_Join.v2.h3_builder import IdentityAssets
|
||||
from ComfyUI_H3_Continuum_Join.v2.prompts import make_prompt_plan
|
||||
from ComfyUI_H3_Continuum_Join.v2 import sequence
|
||||
|
||||
|
||||
class Nested:
|
||||
def __init__(self, parts):
|
||||
self.parts = list(parts)
|
||||
def unbind(self):
|
||||
return self.parts
|
||||
|
||||
|
||||
def _latent(width, height, frames):
|
||||
return {
|
||||
"samples": Nested(
|
||||
(
|
||||
torch.zeros(1, 24, video_latent_t(frames), height // 16, width // 16),
|
||||
torch.zeros(1, 32, 2, audio_latent_t(frames)),
|
||||
)
|
||||
)
|
||||
}
|
||||
|
||||
def __init__(self,parts): self.parts=list(parts)
|
||||
def unbind(self): return self.parts
|
||||
|
||||
def _latent(width,height,frames):
|
||||
return {"samples":Nested((torch.zeros(1,24,video_latent_t(frames),height//16,width//16),torch.zeros(1,32,2,audio_latent_t(frames))))}
|
||||
class FakeClip:
|
||||
def __init__(self, events):
|
||||
self.events = events
|
||||
def tokenize(self, prompt, images):
|
||||
self.events.append(("tokenize", prompt, len(images)))
|
||||
return prompt
|
||||
def encode_from_tokens_scheduled(self, tokens):
|
||||
self.events.append(("encode", tokens))
|
||||
return [[torch.zeros(1, 1, 2), {}]]
|
||||
|
||||
def __init__(self,events): self.events=events
|
||||
def tokenize(self,prompt,images): self.events.append(("tokenize",prompt,len(images))); return prompt
|
||||
def encode_from_tokens_scheduled(self,tokens): self.events.append(("encode",tokens)); return [[torch.zeros(1,1,2),{}]]
|
||||
|
||||
def test_v2_samples_every_chunk_before_any_decode(monkeypatch):
|
||||
events = []
|
||||
width, height = 96, 64
|
||||
fake_model = SimpleNamespace(
|
||||
model=SimpleNamespace(diffusion_model=SimpleNamespace()),
|
||||
model_options={},
|
||||
wrappers={},
|
||||
model_dtype=lambda: torch.bfloat16,
|
||||
model_size=lambda: 0,
|
||||
)
|
||||
assets = IdentityAssets(None, None, None, None, "none")
|
||||
|
||||
monkeypatch.setattr(sequence, "check_comfy_h3_runtime", lambda: [])
|
||||
monkeypatch.setattr(sequence, "patch_model", lambda model, strict, debug: model)
|
||||
def clone_model_for_chunk(
|
||||
model,
|
||||
*,
|
||||
strict,
|
||||
debug,
|
||||
chunk_index,
|
||||
context_frames,
|
||||
):
|
||||
options = dict(model.model_options)
|
||||
transformer_options = dict(options.get("transformer_options") or {})
|
||||
if context_frames is not None:
|
||||
transformer_options[CONTINUUM_INTEROP_KEY] = {
|
||||
"api": 1,
|
||||
"active": True,
|
||||
"min_actual_prefix_steps": 2,
|
||||
}
|
||||
options["transformer_options"] = transformer_options
|
||||
events.append(("clone", chunk_index, context_frames))
|
||||
return SimpleNamespace(
|
||||
model=model.model,
|
||||
model_options=options,
|
||||
wrappers=model.wrappers,
|
||||
model_dtype=model.model_dtype,
|
||||
model_size=model.model_size,
|
||||
)
|
||||
|
||||
monkeypatch.setattr(sequence, "clone_model_for_chunk", clone_model_for_chunk)
|
||||
monkeypatch.setattr(sequence, "prepare_identity_assets", lambda *a, **k: assets)
|
||||
monkeypatch.setattr(sequence, "encode_identity_latents", lambda *a, **k: assets)
|
||||
monkeypatch.setattr(sequence, "empty_h3_latent", _latent)
|
||||
monkeypatch.setattr(sequence, "accelerator_summary", lambda model: "accelerators")
|
||||
|
||||
events=[]; width,height=96,64
|
||||
fake_model=SimpleNamespace(model=SimpleNamespace(diffusion_model=SimpleNamespace()),model_options={},wrappers={},model_dtype=lambda:torch.bfloat16,model_size=lambda:0)
|
||||
assets=IdentityAssets(None,None,None,None,"none")
|
||||
monkeypatch.setattr(sequence,"check_comfy_h3_runtime",lambda:[])
|
||||
monkeypatch.setattr(sequence,"patch_model",lambda model,strict,debug:model)
|
||||
def clone_model_for_chunk(model,*,strict,debug,chunk_index,context_frames):
|
||||
options=dict(model.model_options); transformer_options=dict(options.get("transformer_options") or {})
|
||||
if context_frames is not None: transformer_options[CONTINUUM_INTEROP_KEY]={"api":1,"active":True,"min_actual_prefix_steps":2}
|
||||
options["transformer_options"]=transformer_options; events.append(("clone",chunk_index,context_frames))
|
||||
return SimpleNamespace(model=model.model,model_options=options,wrappers=model.wrappers,model_dtype=model.model_dtype,model_size=model.model_size)
|
||||
monkeypatch.setattr(sequence,"clone_model_for_chunk",clone_model_for_chunk)
|
||||
monkeypatch.setattr(sequence,"prepare_identity_assets",lambda *a,**k:assets)
|
||||
monkeypatch.setattr(sequence,"encode_identity_latents",lambda *a,**k:assets)
|
||||
monkeypatch.setattr(sequence,"empty_h3_latent",_latent)
|
||||
monkeypatch.setattr(sequence,"accelerator_summary",lambda model:"accelerators")
|
||||
def sample_chunk(**kwargs):
|
||||
frames = kwargs["latent"]["samples"].unbind()[0].shape[2]
|
||||
hint = kwargs["model"].model_options["transformer_options"].get(
|
||||
CONTINUUM_INTEROP_KEY
|
||||
)
|
||||
events.append(("sample", int(frames), kwargs["seed"], hint))
|
||||
return kwargs["latent"]
|
||||
|
||||
frames=kwargs["latent"]["samples"].unbind()[0].shape[2]; hint=kwargs["model"].model_options["transformer_options"].get(CONTINUUM_INTEROP_KEY); events.append(("sample",int(frames),kwargs["seed"],hint)); return kwargs["latent"]
|
||||
def decode_sequence(**kwargs):
|
||||
events.append(("decode", len(kwargs["entries"])))
|
||||
images = torch.zeros(362, 2, 2, 3)
|
||||
audio = {"waveform": torch.zeros(1, 2, round(362 / 24 * 32000)), "sample_rate": 32000}
|
||||
return images, audio, []
|
||||
|
||||
monkeypatch.setattr(sequence, "sample_chunk", sample_chunk)
|
||||
monkeypatch.setattr(sequence, "decode_sequence", decode_sequence)
|
||||
|
||||
def unexpected_seam_decode(**kwargs):
|
||||
raise AssertionError("Off must not enter the V2.1 seam decoder")
|
||||
|
||||
monkeypatch.setattr(sequence, "decode_sequence_with_seam", unexpected_seam_decode)
|
||||
|
||||
plan = make_prompt_plan(
|
||||
mode=PROMPT_MODE_FIXED,
|
||||
script="continuous shot",
|
||||
chunks=3,
|
||||
chunk_seconds=5.0,
|
||||
)
|
||||
images, audio, last_state, session, report = sequence.run_sequence(
|
||||
model=fake_model,
|
||||
clip=FakeClip(events),
|
||||
video_vae=object(),
|
||||
audio_vae=object(),
|
||||
sampler=object(),
|
||||
sigmas=torch.tensor([1.0, 0.0]),
|
||||
first_frame=None,
|
||||
last_frame=None,
|
||||
prompt_plan=plan,
|
||||
width=width,
|
||||
height=height,
|
||||
continuity=V2_CONTINUITY_OPTIONS[1],
|
||||
base_seed=42,
|
||||
audio_continuity=True,
|
||||
exact_total_duration=True,
|
||||
diagnostics_mode=DIAGNOSTICS_BASIC,
|
||||
reroll_from_chunk=0,
|
||||
reroll_nonce=0,
|
||||
strict_compatibility=True,
|
||||
debug=False,
|
||||
)
|
||||
|
||||
sample_positions = [i for i, event in enumerate(events) if event[0] == "sample"]
|
||||
decode_position = next(i for i, event in enumerate(events) if event[0] == "decode")
|
||||
assert len(sample_positions) == 3
|
||||
assert max(sample_positions) < decode_position
|
||||
sample_events = [event for event in events if event[0] == "sample"]
|
||||
events.append(("decode",len(kwargs["entries"]))); return torch.zeros(362,2,2,3),{"waveform":torch.zeros(1,2,round(362/24*32000)),"sample_rate":32000},[]
|
||||
monkeypatch.setattr(sequence,"sample_chunk",sample_chunk); monkeypatch.setattr(sequence,"decode_sequence",decode_sequence)
|
||||
monkeypatch.setattr(sequence,"decode_sequence_with_seam",lambda **kwargs: (_ for _ in ()).throw(AssertionError("Off must not enter the V2.1 seam decoder")))
|
||||
plan=make_prompt_plan(mode=PROMPT_MODE_FIXED,script="continuous shot",chunks=3,chunk_seconds=5.0)
|
||||
images,audio,last_state,session,report=sequence.run_sequence(model=fake_model,clip=FakeClip(events),video_vae=object(),audio_vae=object(),sampler=object(),sigmas=torch.tensor([1.0,0.0]),first_frame=None,last_frame=None,prompt_plan=plan,width=width,height=height,continuity=V2_CONTINUITY_OPTIONS[1],base_seed=42,audio_continuity=True,exact_total_duration=True,diagnostics_mode=DIAGNOSTICS_BASIC,reroll_from_chunk=0,reroll_nonce=0,strict_compatibility=True,debug=False)
|
||||
sample_positions=[i for i,e in enumerate(events) if e[0]=="sample"]; decode_position=next(i for i,e in enumerate(events) if e[0]=="decode")
|
||||
assert len(sample_positions)==3 and max(sample_positions)<decode_position
|
||||
sample_events=[e for e in events if e[0]=="sample"]
|
||||
assert sample_events[0][3] is None
|
||||
assert sample_events[1][3]["min_actual_prefix_steps"] == 2
|
||||
assert sample_events[2][3]["min_actual_prefix_steps"] == 2
|
||||
clone_events = [event for event in events if event[0] == "clone"]
|
||||
assert [event[2] for event in clone_events] == [None, 22, 22]
|
||||
# Fixed mode encodes its shared text conditioning only once.
|
||||
assert sum(event[0] == "encode" for event in events) == 1
|
||||
assert images.shape[0] == 360
|
||||
assert audio["waveform"].shape[-1] == 480000
|
||||
assert last_state["clip_index"] == 3
|
||||
assert len(session["chunks"]) == 3
|
||||
assert sample_events[1][3]["min_actual_prefix_steps"]==2 and sample_events[2][3]["min_actual_prefix_steps"]==2
|
||||
assert [e[2] for e in events if e[0]=="clone"]==[None,22,22]
|
||||
assert sum(e[0]=="encode" for e in events)==1
|
||||
assert images.shape[0]==360 and audio["waveform"].shape[-1]==480000
|
||||
assert last_state["clip_index"]==3 and len(session["chunks"])==3
|
||||
assert "call-local MODEL clone per chunk" in report
|
||||
|
||||
Reference in New Issue
Block a user