zhenzhen-minimax-h3-ow-video-lowprice

This is the "slow and steady" sibling of the fast H3 node: Comfly_minimax_h3_ow_video_lowprice ("zhenzhen-minimax-h3-ow-video-lowprice") covers the standard-quality tier of MiniMax H3 video - minimax-h3-ow-t2v (text to video), minimax-h3-ow-i2v (image to video), and minimax-h3-ow-r2v (reference to video). Same family, smaller model list, and if you've already used the fast node the layout will feel familiar.

Why would you reach for the standard tier over the fast one? Because "fast" usually means "we'll take a quality cut." When the shot matters - a hero moment you're actually going to use - the standard endpoints often behave better. The two nodes are meant to sit side by side in the same workflow: prototype with fast, then render the keeper at standard quality. The pack's own changelog shows both tiers tracking MiniMax's releases, including the 768p resolution support for the earlier H3 nodes.

It's part of the T8mars/Comfyui-zhenzhen pack, the "Comfly" API-wrapper family routed through the author's paid reseller service. As a "lowprice" node it uses the cheaper China-facing endpoint (api.seedance.nz) and takes its key from the shared zhenzhen-seedance2-low-price-api-settings node via api_config. Standard submit → poll → download, with a real VIDEO tensor at the end.

The inputs

• model - required: t2v, i2v, or r2v.
• prompt - the scene. For r2v, describe what the reference should stay consistent with.
• seconds - 5, 10, or 15.
• resolution - 480p or 720p.
• ratio - 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9.
• image1 - a single reference/first-frame image (this tier takes one, where the fast node takes up to nine - a real hint about scope).
• api_config, skip_error, and a cache-control seed round it out.

Outputs

• video - the VIDEO output for a save/preview node.
• video_url - the hosted file.
• task_id - for the site's async task list.
• response - raw payload.

Installing it

cd ComfyUI/custom_nodes
git clone https://github.com/T8mars/Comfyui-zhenzhen
# restart ComfyUI

Or ComfyUI Manager → "Comfyui-zhenzhen". Then a zhenzhen-seedance2-low-price-api-settings node with your key, wired into api_config.

The honest part

The standard tier is the "when quality beats speed" slot, and for r2v character consistency jobs it's where you'll live. Caveats are the pack's usual trio: it's a reseller in the middle (your prompts and images leave your machine), upstream 500s are typically not yours (rerun), and per-call video cost accumulates if you're not careful - a 15-second render is the expensive end of a low-price node. And since MiniMax H3's open weights ship with licensing that excludes the US and EU, plenty of people literally cannot run this locally even if they have the VRAM. For them this node isn't a convenience, it's the only door.