zhenzhen-wan-3.0-video-lowprice（8合1）

This is the biggest single node in the pack's low-price family, and the README's headline feature: zhenzhen-wan-3.0-video-lowprice（4合1） - four Wan 3.0 video models behind one model dropdown. wan-3.0-i2v and wan-3.0-r2v for the standard tier, wan-3.0-global-i2v and wan-3.0-global-r2v for the overseas tier. Image-to-video takes a first frame and an optional last frame; reference-to-video takes up to ten images, five videos, five audio clips, or a mutually exclusive file or web URL. It's a lot of capability in one box, and it defaults to 480P precisely so you can experiment cheaply before spending on resolution.

Like everything with "lowprice" in it, this runs on Zhenzhen's domestic storefront (api.seedance.nz) and shares its settings-node plumbing.

How it works

Pick a model, write a prompt, connect what that model needs, and the node submits and polls until the clip's done. Outputs: video, video_url, task_id, response. The prompt tooltip spells out the rules: up to 20,000 characters; R2V prompts are required while I2V ones are optional; and R2V references are addressed by upload order - Image 1, Video 1, Audio 1 - which matters when you're mixing media in one prompt.

The inputs that matter:

• model - the i2v / r2v / global-i2v / global-r2v choice. Global tiers for non-mainland users.
• image1 / image2 - in I2V, image1 is the required first frame and image2 is the optional last frame. In R2V, up to ten images.
• video1–video5, audio1–audio5 - R2V reference media. This is the "multi-modal" part.
• file_url / link_url - R2V-only, mutually exclusive: a public file URL or a webpage URL as reference.
• seconds - from auto up through long clips. resolution - 480P / 720P / 1080P. ratio - adaptive plus the usual set. generate_audio is on by default.
• enable_thinking - only applies to the overseas models, and auto-enables when Global R2V gets a file_url or link_url.

Installing and setting up

Install through ComfyUI Manager (search Comfyui-zhenzhen) or:

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

Restart ComfyUI. No model files. Connect the Comfly Seedance2 Low Price Settings node's api_config or set SEEDANCE_API_KEY. The pack ships example workflows for all four modes in its workflow folder, and they deliberately don't embed your API key - a nice touch from the author.

Troubleshooting

The config-node requirement is the family's universal tripwire, same as the others. For this node specifically, watch the R2V reference order - the prompt refers to "Image 1, Video 1, Audio 1" in upload order, and if you plug a video into video2 expecting it to be "Video 2," make sure the upstream order matches what you describe. And in I2V, forgetting image1 on an i2v model is the classic "why is it empty" moment. skip_error is available; keep it off while debugging so you actually see errors, then on for batch runs.