用 ComfyUI API 搭建 MiniMax-H3 视频音频生成流水线

In this tutorial, we implement an end-to-end MiniMax-H3 video generation workflow using ComfyUI as a headless inference backend. We configure the environment around GPU memory, disk capacity, model precision, resolution, duration, sampling strategy, and multiple generation modes, while dynamically selecting an appropriate weight profile based on the available hardware. We install and launch ComfyUI programmatically, download the required diffusion, text-encoder, video-VAE, and audio-VAE weights from Hugging Face, and communicate with the running server through its HTTP and WebSocket APIs. We also construct the ComfyUI execution graph directly in Python, validate node schemas against the live /object_info endpoint, and support text-to-video, first- and last-frame-conditioned generation, and reference-image-conditioned generation. By combining automated model setup, schema-aware graph construction, joint video-audio decoding, progress monitoring, and output collection, we create a reproducible pipeline for experimenting with MiniMax-H3 without relying on the graphical ComfyUI interface.

import json, os, re, shutil, subprocess, sys, time, uuid, urllib.request, urllib.error
from pathlib import Path
CFG = {
   "MODE": "t2v",
   "PROMPT": (
       "Realistic live-action cinematic look. A lone lighthouse keeper on a storm-lashed "
       "cliff at dusk, anamorphic lens, shallow depth of field, film grain, volumetric sea spray.\n"
       "[0s-2s] Wide shot: waves detonate against black rock, the lighthouse beam sweeps the frame.\n"
       "[2s-4s] Medium shot: the keeper braces against the wind, coat snapping, rain on his face.\n"
       "[4s-5s] Close up: he squints into the dark and says \"She's holding.\"\n"
       "Camera: hard cuts between shots, slight handheld jitter, no dissolves.\n"
       "Audio: roaring surf and howling wind throughout, low cello drone underneath, "
       "a heavy wave impact on each cut, the line delivered clearly over the storm.\n"
       "No text, subtitles, logos or watermarks."
   ),
   "ASPECT": (16, 9),
   "MEGAPIXELS": 0.4,
   "SECONDS": 5.0,
   "SEED": 556589502035082,
   "STEPS": 20,
   "SAMPLER": "res_multistep",
   "SCHEDULER": "simple",
   "FIRST_FRAME": None,
   "LAST_FRAME": None,
   "REF_IMAGES": [],
   "REF_IMAGE_SIZE": "match",
   "SIGMA_SHIFT": None,
   "TURBO_LORA": False,
   "TURBO_STEPS": 8,
   "TURBO_SAMPLER": "euler",
   "TURBO_SCHEDULER": "beta",
   "COMFY_DIR": "/content/ComfyUI",
   "OUT_DIR": "/content/outputs",
   "MODELS_ROOT": "/content/models",
   "PORT": 8188,
   "HF_TOKEN": os.environ.get("HF_TOKEN", ""),
   "SKIP_INSTALL": False,
}
REPO = "Comfy-Org/MiniMax-H3"
API = f"http://127.0.0.1:{CFG['PORT']}"
PROFILES = [
   dict(name="quality", min_vram=70,
        unet_fl="minimax_h3_fl2va_bf16.safetensors",
        unet_ref="minimax_h3_ref2va_bf16.safetensors",
        te="qwen3vl_32b_minimax_h3_int8_convrot.safetensors",
        flags=["--normalvram"]),
   dict(name="balanced", min_vram=38,
        unet_fl="minimax_h3_fl2va_pruned_int8_convrot.safetensors",
        unet_ref="minimax_h3_ref2va_pruned_int8_convrot.safetensors",
        te="qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
        flags=["--normalvram", "--cache-none"]),
   dict(name="squeeze", min_vram=20,
        unet_fl="minimax_h3_fl2va_pruned_fp8_scaled.safetensors",
        unet_ref="minimax_h3_ref2va_pruned_fp8_scaled.safetensors",
        te="qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors",
        flags=["--lowvram", "--cache-none", "--disable-smart-memory"]),
]
VAE_VIDEO = "minimax_h3_video_vae_fp16.safetensors"
VAE_AUDIO = "minimax_h3_audio_vae_fp32.safetensors"
def sh(cmd, cwd=None, check=True, quiet=False):
   """Run a shell command, streaming output."""
   print(f"$ {cmd}")
   p = subprocess.run(cmd, shell=True, cwd=cwd,
                      stdout=subprocess.DEVNULL if quiet else None,
                      stderr=subprocess.STDOUT if quiet else None)
   if check and p.returncode != 0:
       raise RuntimeError(f"command failed ({p.returncode}): {cmd}")
def get_json(path, payload=None, timeout=30):
   url = f"{API}{path}"
   data = json.dumps(payload).encode() if payload is not None else None
   req = urllib.request.Request(url, data=data,
                                headers={"Content-Type": "application/json"})
   with urllib.request.urlopen(req, timeout=timeout) as r:
       body = r.read()
   return json.loads(body) if body else {}
def align_frames(seconds, fps=24):
   """H3 consumes frame counts on the 17k+5 grid. Snap upward."""
   n = max(5, int(round(seconds * fps)))
   while n % 17 != 5:
       n += 1
   return n
def h3_canvas(aspect=(16, 9), megapixels=0.98, multiple=32):
   """Mirror of ComfyUI's ResolutionSelector + H3's 768*1344 area cap."""
   ar = aspect[0] / aspect[1]
   total = megapixels * 1e6
   h = (total / ar) ** 0.5
   w = ar * h
   cap = 768 * 1344
   if w * h > cap:
       s = (cap / (w * h)) ** 0.5
       w, h = w * s, h * s
   r = lambda v: max(multiple, int(round(v / multiple)) * multiple)
   return r(w), r(h)
def preflight():
   try:
       import torch
   except ImportError:
       raise SystemExit("PyTorch missing — run this in a Colab GPU runtime.")
   if not torch.cuda.is_available():
       raise SystemExit("No CUDA device. Runtime > Change runtime type > GPU (A100).")
   name = torch.cuda.get_device_name(0)
   vram = torch.cuda.get_device_properties(0).total_memory / 1e9
   free_disk = shutil.disk_usage("/content").free / 1e9
   bf16 = torch.cuda.is_bf16_supported()
   print(f"GPU        : {name}  ({vram:.1f} GB VRAM, bf16={bf16})")
   print(f"Free disk  : {free_disk:.1f} GB")
   if not bf16:
       raise SystemExit(
           "This GPU has no bf16 support (T4/K80). MiniMax-H3 will not run here.\n"
           "Switch to an A100/L4/H100 runtime."
       )
   profile = next((p for p in PROFILES if vram >= p["min_vram"]), None)
   if profile is None:
       raise SystemExit(
           f"{vram:.0f} GB VRAM is below the ~20 GB floor for the smallest H3 build."
       )
   if free_disk < 45:
       print("WARNING: <45 GB free. Point MODELS_ROOT at Drive or expect a disk-full error.")
   print(f"Profile    : {profile['name']}  (unet={profile['unet_fl']}, te={profile['te']})")
   return profile

We define the core MiniMax-H3 configuration, model profiles, generation parameters, and shared utility functions used throughout the workflow. We calculate valid frame counts and canvas dimensions while checking GPU capability, available VRAM, BF16 support, and disk space before inference begins. We also automatically select the most appropriate model profile so the pipeline matches the hardware available in our Colab runtime.