Release H3 Continuum V3.3.0

This commit is contained in:
ukr8b3g-cmyk
2026-08-16 20:32:47 +09:00
parent a908e4884f
commit fb22c20149
38 changed files with 3598 additions and 363 deletions
+43 -11
View File
@@ -67,19 +67,19 @@ def _preserved_prefix(*,session,prompt_hashes,chunks,reroll_from_chunk,width,hei
elif reroll_from_chunk>0: notes.append(f"preserved chunks 1-{len(preserved)}; regenerated from chunk {reroll_from_chunk}")
return preserved,notes
def _conditioning_cache(*,clip,prompts,assets,final_has_last_frame,reference_assets=None):
def _conditioning_cache(*,clip,prompts,assets,final_has_last_frame,reference_assets=None,reference_audio_assets=None,timeline_video_assets=None):
cache={}; final_index=len(prompts)-1
for index,prompt in enumerate(prompts):
include_last=bool(final_has_last_frame and index==final_index); key=(prompt,include_last)
if key in cache: continue
if reference_assets is not None:
from ..reference import encode_reference_prompt
cache[key]=encode_reference_prompt(clip,prompt,reference_assets)
cache[key]=encode_reference_prompt(clip,prompt,reference_assets,reference_audio_assets=reference_audio_assets,timeline_video_assets=timeline_video_assets)
else:
cache[key]=encode_prompt_conditioning(clip,prompt,first_image=assets.first_image,last_image=assets.last_image if include_last else None)
cache[key]=encode_prompt_conditioning(clip,prompt,first_image=assets.first_image,last_image=assets.last_image if include_last else None,reference_audio_assets=reference_audio_assets,timeline_video_assets=timeline_video_assets)
return cache
def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,sigmas:torch.Tensor,first_frame:torch.Tensor|None,last_frame:torch.Tensor|None,prompt_plan:dict[str,Any],width:int,height:int,continuity:str,base_seed:int,audio_continuity:bool,exact_total_duration:bool,diagnostics_mode:str,reroll_from_chunk:int,reroll_nonce:int,strict_compatibility:bool,debug:bool,seam_correction:str=SEAM_CORRECTION_OFF,enable_preview:bool=True,session:dict[str,Any]|None=None,initial_state:dict[str,Any]|None=None,latent_only:bool=False,reference_assets=None):
def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,sigmas:torch.Tensor,first_frame:torch.Tensor|None,last_frame:torch.Tensor|None,prompt_plan:dict[str,Any],width:int,height:int,continuity:str,base_seed:int,audio_continuity:bool,exact_total_duration:bool,diagnostics_mode:str,reroll_from_chunk:int,reroll_nonce:int,strict_compatibility:bool,debug:bool,seam_correction:str=SEAM_CORRECTION_OFF,enable_preview:bool=True,session:dict[str,Any]|None=None,initial_state:dict[str,Any]|None=None,latent_only:bool=False,reference_assets=None,reference_audio_source=None,reference_audio_vae=None,timeline_video_source=None):
from ..conditioning import detect_conditioning_mode, conditioning_mode_label
from ..run_storage import get_active_run_storage
storage_controller=get_active_run_storage()
@@ -97,15 +97,27 @@ def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,si
from ..reference import validate_reference_prompts
if first_frame is not None or last_frame is not None: raise SequenceRuntimeError("Reference images cannot be combined with First Frame or Last Frame in V3.2")
reference_warning=validate_reference_prompts(prompts,reference_assets.count)
from ..reference_audio import (
combine_reference_audio_identity,
validate_reference_audio_prompts,
)
reference_audio_warning=validate_reference_audio_prompts(prompts,reference_audio_source)
from ..timeline_video import (
combine_timeline_video_identity,
validate_timeline_video_prompts,
)
timeline_video_warning=validate_timeline_video_prompts(prompts,timeline_video_source)
decode_estimate_gib=0.0; available_ram_gib=None
if not latent_only: decode_estimate_gib,available_ram_gib=_check_decode_memory_budget(width=width,height=height,chunks=chunks,chunk_seconds=chunk_seconds)
issues=check_comfy_h3_runtime()
if issues and strict_compatibility: raise SequenceRuntimeError("H3 runtime is incompatible: "+"; ".join(issues))
assets=prepare_identity_assets(video_vae,width=width,height=height,first_frame=first_frame,last_frame=last_frame,encode_latents=False)
sequence_identity_hash=reference_assets.combined_hash if reference_assets is not None else assets.identity_hash
visual_identity_hash=reference_assets.combined_hash if reference_assets is not None else assets.identity_hash
sequence_identity_hash=combine_reference_audio_identity(visual_identity_hash,reference_audio_source)
sequence_identity_hash=combine_timeline_video_identity(sequence_identity_hash,timeline_video_source)
current_model_fingerprint=model_fingerprint(model,extra_wrapper_keys=("h3_continuum_join.apply_model.v1",))
if storage_controller is not None:
stored_session=storage_controller.prepare(model=model,model_fingerprint_value=current_model_fingerprint,clip=clip,video_vae=video_vae,sampler=sampler,sigmas=sigmas,prompt_plan=plan,width=width,height=height,chunk_seconds=chunk_seconds,continuity=continuity,audio_continuity=audio_continuity,base_seed=base_seed,reroll_from_chunk=reroll_from_chunk,reroll_nonce=reroll_nonce,first_frame_hash=assets.first_frame_hash,last_frame_hash=assets.last_frame_hash,identity_hash=sequence_identity_hash,strict_compatibility=strict_compatibility,existing_session=session,reference_contract=reference_assets.contract if reference_assets is not None else None,conditioning_mode=conditioning_mode)
stored_session=storage_controller.prepare(model=model,model_fingerprint_value=current_model_fingerprint,clip=clip,video_vae=video_vae,sampler=sampler,sigmas=sigmas,prompt_plan=plan,width=width,height=height,chunk_seconds=chunk_seconds,continuity=continuity,audio_continuity=audio_continuity,base_seed=base_seed,reroll_from_chunk=reroll_from_chunk,reroll_nonce=reroll_nonce,first_frame_hash=assets.first_frame_hash,last_frame_hash=assets.last_frame_hash,identity_hash=sequence_identity_hash,strict_compatibility=strict_compatibility,existing_session=session,reference_contract=reference_assets.contract if reference_assets is not None else None,conditioning_mode=conditioning_mode,reference_audio_contract=reference_audio_source.contract if reference_audio_source is not None else None,reference_audio_vae=reference_audio_vae,timeline_video_contract=timeline_video_source.contract if timeline_video_source is not None else None)
reroll_nonce=storage_controller.effective_reroll_nonce
if stored_session is not None: session=stored_session
accelerators=accelerator_summary(model)
@@ -114,7 +126,13 @@ def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,si
preserved,reuse_notes=_preserved_prefix(session=session,prompt_hashes=prompt_hashes,chunks=chunks,reroll_from_chunk=effective_reroll_from_chunk,width=width,height=height,chunk_seconds=chunk_seconds,identity_hash=sequence_identity_hash)
if reference_assets is not None:
reuse_notes.insert(0,f"Reference conditioning: {reference_assets.count} image(s), size={reference_assets.size_mode}; persistent across all chunks.")
if reference_warning: reuse_notes.append("Warning: "+reference_warning)
if reference_warning: reuse_notes.append(reference_warning)
if reference_audio_source is not None:
reuse_notes.insert(0,"Reference Audio 1 conditioning: persistent across all chunks.")
if reference_audio_warning: reuse_notes.append(reference_audio_warning)
if timeline_video_source is not None:
reuse_notes.insert(0,f"Timeline Video conditioning: chunk-local slices, size={timeline_video_source.size_mode}, resolved={timeline_video_source.target_width}x{timeline_video_source.target_height}.")
if timeline_video_warning: reuse_notes.append(timeline_video_warning)
if session is not None:
old_fingerprint=str(session.get("model_fingerprint",""))
if old_fingerprint and old_fingerprint!=current_model_fingerprint: reuse_notes.append("model/accelerator fingerprint differs from the saved session; accepted chunks were kept")
@@ -124,7 +142,12 @@ def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,si
if reference_assets is not None:
from ..reference import encode_reference_latents
reference_assets=encode_reference_latents(video_vae,reference_assets)
cache=_conditioning_cache(clip=clip,prompts=prompts,assets=assets,final_has_last_frame=last_frame is not None,reference_assets=reference_assets)
reference_audio_assets=None
if reference_audio_source is not None:
from ..reference_audio import encode_reference_audio
reference_audio_assets=encode_reference_audio(reference_audio_vae,reference_audio_source)
if timeline_video_source is None:
cache=_conditioning_cache(clip=clip,prompts=prompts,assets=assets,final_has_last_frame=last_frame is not None,reference_assets=reference_assets,reference_audio_assets=reference_audio_assets)
entries=preserved[:]; previous_state=None
if entries: previous_state=entry_to_state(entries[-1])
elif initial_state is not None:
@@ -133,12 +156,18 @@ def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,si
initial_frame_count=align_frame_count_up(int(round(chunk_seconds*FPS))); retained_frames=sum(int(entry["plan"]["net_frames"]) for entry in entries); sampling_reports=[]
for sequence_index in range(len(entries),chunks):
prompt=prompts[sequence_index]; prompt_hash_value=prompt_hashes[sequence_index]; is_final=sequence_index==chunks-1; effective_reroll_nonce=int(reroll_nonce) if int(reroll_from_chunk)>0 and sequence_index+1>=int(reroll_from_chunk) else 0; seed=derive_chunk_seed(base_seed,sequence_index,effective_reroll_nonce); motion_score=0.0; video_context=None; audio_context=None; context_before=None
timeline_video_assets=None
chunk_cache=cache
if timeline_video_source is not None:
from ..timeline_video import encode_timeline_video_chunk
timeline_video_assets=encode_timeline_video_chunk(video_vae,timeline_video_source,sequence_index)
chunk_cache=_conditioning_cache(clip=clip,prompts=[prompt],assets=assets,final_has_last_frame=bool(last_frame is not None and is_final),reference_assets=reference_assets,reference_audio_assets=reference_audio_assets,timeline_video_assets=timeline_video_assets)
if previous_state is None:
total_frames=initial_frame_count; latent=empty_h3_latent(width,height,total_frames); conditioning=attach_keyframes(cache[(prompt,bool(last_frame is not None and is_final))],frame_count=total_frames,first_latent=assets.first_latent,last_latent=assets.last_latent if is_final else None); clip_index=1; context_frames=0
total_frames=initial_frame_count; latent=empty_h3_latent(width,height,total_frames); conditioning=attach_keyframes(chunk_cache[(prompt,bool(last_frame is not None and is_final))],frame_count=total_frames,first_latent=assets.first_latent,last_latent=assets.last_latent if is_final else None); clip_index=1; context_frames=0
chunk_plan=make_plan(continuation=False,clip_index=clip_index,total_frames=total_frames,trim_frames=0,width=width,height=height,context_frames=5,state_capacity_frames=largest_context_capacity(total_frames),requested_extend_seconds=chunk_seconds,debug=debug); reason="initial clip"
else:
context_frames,motion_score,reason=choose_context_frames(continuity,previous_state); desired_cumulative=int(round((sequence_index+1)*chunk_seconds*FPS)); requested_new_frames=max(1,desired_cumulative-retained_frames); shape=make_extension_shape(context_frames,requested_new_frames/FPS); latent=empty_h3_latent(width,height,shape.total_frames)
base_conditioning=attach_keyframes(cache[(prompt,bool(last_frame is not None and is_final))],frame_count=shape.total_frames,first_latent=assets.first_latent,last_latent=assets.last_latent if is_final else None)
base_conditioning=attach_keyframes(chunk_cache[(prompt,bool(last_frame is not None and is_final))],frame_count=shape.total_frames,first_latent=assets.first_latent,last_latent=assets.last_latent if is_final else None)
video_context,audio_context,grid_offset=select_context(previous_state,context_frames,include_audio=bool(audio_continuity)); context_before=context_fingerprint(video_context,audio_context)
conditioning=prepare_conditioning(base_conditioning,video_context=video_context,audio_context=audio_context,audio_grid_offset=grid_offset,context_frames=context_frames,new_frame_count=shape.total_frames,first_frame_policy=POLICY_REPLACE,preserve_last_frame=True)
clip_index=int(previous_state["clip_index"])+1; chunk_plan=make_plan(continuation=True,clip_index=clip_index,total_frames=shape.total_frames,trim_frames=context_frames,width=width,height=height,context_frames=context_frames,state_capacity_frames=largest_context_capacity(shape.net_new_frames),requested_extend_seconds=chunk_seconds,debug=debug)
@@ -149,11 +178,14 @@ def run_sequence(*,model:Any,clip:Any,video_vae:Any,audio_vae:Any,sampler:Any,si
if storage_controller is not None: storage_controller.commit_chunk(entry, position=sequence_index)
retained_frames+=int(chunk_plan["net_frames"])
sampling_reports.append(f"chunk {sequence_index+1}/{chunks}: seed={seed}, frames={chunk_plan['total_frames']}, trim={chunk_plan['trim_frames']}, retained_total={retained_frames}, context={context_frames} ({reason}), motion={motion_score:.6f}, "+(f"interop=emitted actual_prefix={CONTINUUM_ACTUAL_PREFIX_STEPS} consumer=not_observable" if context_before is not None else "interop=not_emitted"))
del sampled,latent,conditioning,chunk_model
del sampled,latent,conditioning,chunk_model,chunk_cache
if timeline_video_assets is not None: del timeline_video_assets
if len(entries)!=chunks: raise SequenceRuntimeError(f"internal sequence length mismatch: expected {chunks}, got {len(entries)}")
if latent_only:
last_state=entry_to_state(entries[-1]); parent_id=session.get("session_id") if session is not None else None
settings={"continuity":continuity,"audio_continuity":bool(audio_continuity),"exact_total_duration":False,"prompt_mode":plan["mode"],"conditioning_mode":conditioning_mode,"base_seed":int(base_seed),"reroll_nonce":int(reroll_nonce),"diagnostics_mode":diagnostics_mode,"initial_state_source":initial_state is not None,"latent_first":True,"first_frame_hash":assets.first_frame_hash,"last_frame_hash":assets.last_frame_hash,"reference_contract":reference_assets.contract if reference_assets is not None else None}
if reference_audio_source is not None: settings["reference_audio_contract"]=reference_audio_source.contract
if timeline_video_source is not None: settings["timeline_video_contract"]=timeline_video_source.contract
new_session=make_session(chunks=entries,width=width,height=height,chunk_seconds=chunk_seconds,identity_hash=sequence_identity_hash,model_fingerprint_value=current_model_fingerprint,parent_session_id=parent_id,reroll_from_chunk=int(reroll_from_chunk),settings=settings)
report_lines=[f"H3 Continuum V3 {PACKAGE_VERSION}",f"Conditioning mode: {conditioning_mode_label(conditioning_mode)}.",prompt_plan_report(plan),"Decode: external ComfyUI Core VAE nodes; full raw AV chunks retained.",accelerators,"Execution: conditioning precomputed; single call-local MODEL clone per chunk; no internal VAE decode.",*reuse_notes]
if diagnostics_mode!=DIAGNOSTICS_OFF: report_lines.extend(sampling_reports)