zhenzhen-image-gk-v2-lowprice

Comfly_zhenzhen_image_gk_v2_lowprice is the pure text-to-image half of the GK V2 family - no edit mode, no references, just prompt in, images out. It's the node you reach for when you want a batch of options fast and cheap: n goes up to 12 images in one run, size covers the seven practical ratios, and that's about the whole interface. In a pack where some nodes have sixteen reference inputs and four video modes, this one is refreshingly narrow.

It's a domestic-storefront (api.seedance.nz) low-price node like its siblings, so same plumbing, same cheap credits. The whole job is text-to-image; the model does the rest.

How it works

Write a prompt, pick a size, set how many you want, run. Outputs: image, image_url, task_id, and response.

Inputs worth touching:

• prompt - the only creative input. It's the entire node's personality.
• size - 1:1 / 2:3 / 3:2 / 3:4 / 4:3 / 9:16 / 16:9. No adaptive and no custom - pick a canvas.
• n - 1 to 12 images per run. Each image is a separate credit charge, so this is also your cost dial: 12 images is 12× the price of one.

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. One settings node serves the whole family.

Troubleshooting

The family tripwire applies - run without api_config and you get "empty api_key" immediately. Beyond that, this node's own gotcha is the n dial: people set 12 "just to see options," burn twelve credits, and then complain the pack is expensive. Start at 3, pick a winner, go again. The skip_error toggle is available for batch runs where one failed image shouldn't kill the queue - but with n batches, remember a failure mid-batch has already spent credits on whatever succeeded.

If you're choosing between this and GK V1.5: V2 is the newer model, handles prompts a bit better, and gives you more images per run. V1.5 is cheaper per image if your use case is dead simple. For everything else - editing, references, bigger resolutions - the G-2, G-V2, and NB nodes in the same pack have you covered.