Nodes/H3-AutoPromptChain/H3 Auto Prompt Chain v2
ComfyUI Node

H3 Auto Prompt Chain v2

Optimized one-click H3 prompt-list chain: dynamic per-shot step/context budgets, direct AV latent continuation, resumable latent saves, timing profiler and one final memory-bounded decode.

By misutesu-desu·Created 9 days ago·Updated 9 days ago· 6
H3 Auto Prompt Chain v2
  • model
  • clip
  • video_vae
  • audio_vae
  • sampler
  • first_frame
  • video_path
  • run_info
  • profile_path
global_promptGLOBAL CONTINUITY: Preserve established character identity, facial features, body proportions, wardrobe, scene geometry, object state, lighting logic and cinematic style across shots. Natural temporal motion and coherent native audio. non_diegetic_music: N/A
shot_prompts[BALANCED] SHOT 01: A woman walks slowly through a quiet apartment toward the window. --- [FAST] SHOT 02: She reaches the window and looks down at the street. --- [MOTION] SHOT 03: She suddenly turns and walks quickly toward the table.
width608
height352
default_duration_seconds8.0
default_steps6
schedulersimple
default_context_frames22
manual_tail_frames7
base_seed123456789
start_clip1
latent_prefixh3_autochain/clip
output_prefixvideo/H3_AUTO_CHAIN_FINAL
crf18
CategoryMiniMax H3/automation

Inputs (20)

NameTypeDefaultDescription
modelMODEL
clipCLIP
video_vaeVAE
audio_vaeVAE
samplerSAMPLER
global_promptSTRINGGLOBAL CONTINUITY: Preserve established character identity, facial features, body proportions, wardrobe, scene geometry, object state, lighting logic and cinematic style across shots. Natural temporal motion and coherent native audio. non_diegetic_music: N/A
shot_promptsSTRING[BALANCED] SHOT 01: A woman walks slowly through a quiet apartment toward the window. --- [FAST] SHOT 02: She reaches the window and looks down at the street. --- [MOTION] SHOT 03: She suddenly turns and walks quickly toward the table.Separate multiline shots with ---. Optional leading tags: [FAST], [BALANCED], [QUALITY], [dur=10.1], [steps=4], [ctx=5], [tail=7].
widthINT60832–4096
heightINT35232–4096
default_duration_secondsFLOAT8.05–15
default_stepsINT61–40
schedulerCOMBOsimple9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3
default_context_framesCOMBO223 options: 5, 22, 39
manual_tail_framesINT70–68Fast no-decode handover tail. 7 mirrors the suite's balanced no-lock fallback request before phase alignment.
base_seedINT1234567890–18446744073709550000
start_clipINT11–801=fresh run. If clip N failed, keep saved latents and resume with N.
latent_prefixSTRINGh3_autochain/clip
output_prefixSTRINGvideo/H3_AUTO_CHAIN_FINAL
crfINT180–51
first_frameoptIMAGEOptional first-frame anchor for clip 1. Leave disconnected for pure T2V.

Outputs (3)

NameTypeDescription
video_pathSTRING
run_infoSTRING
profile_pathSTRING