Nodes/Comfyui-zhenzhen/Zhenzhen Nano Banana Pro Edit Fal
ComfyUI Node

Zhenzhen Nano Banana Pro Edit Fal

Nano Banana Pro at 4K through FAL — mind the download size

By T8mars·Created about a year ago·Updated 2 days ago· 740
Zhenzhen Nano Banana Pro Edit Fal
  • image1
  • image2
  • image3
  • image4
  • image5
  • image6
  • image7
  • image8
  • images
  • image_urls
  • response
prompt
api_key
num_images1
aspect_ratioauto
resolution1K
output_formatpng
safety_tolerance4
system_prompt
seed0
image_wayimage_url
poll_interval3
max_poll_attempts1200
skip_errorfalse

Nano Banana Pro is Google's flagship image model - 4K native output, "thinking" before it generates, up to fourteen reference images - and Comfly_nano_banana_pro_fal ("Zhenzhen Nano Banana Pro Edit Fal") is the FAL-route node for it. It's structurally identical to the Banana 2 FAL node: same eight reference slots, same num_images batching, same 1K/2K/4K resolution switch, same FAL polling machinery. The difference is which flagship you're calling and how expensive its output is.

It's a FAL-class node in the T8mars/Comfyui-zhenzhen pack, the "Comfly" API-wrapper family that calls the author's paid reseller service. Key goes into api_key directly; billing is pre-deduct and settles after. Submit → poll → download, results as IMAGE.

The inputs that matter

  • prompt - required. Pro's "thinking" behavior rewards detailed instructions; it reasons before generating.
  • image1image8 - reference images for edit jobs.
  • num_images - 1 to 4 per call.
  • aspect_ratio - auto plus the standard set.
  • resolution - 1K (default), 2K, 4K.
  • output_format - png/jpeg/webp.
  • safety_tolerance - 1 to 6; default 4.
  • system_prompt - an optional instruction to steer the model's persona/style.
  • image_way - image_url or base64 for references.
  • seed - real FAL seed (0–65535, 0 = random).
  • poll_interval / max_poll_attempts - defaults 3s × 1200 = a one-hour timeout ceiling.

Outputs

  • images - the result(s) as IMAGE.
  • image_urls - hosted URLs as a string.
  • response - the 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 key from the author's site into api_key.

The honest part

The one thing that actually distinguishes this node from its siblings is the 4K download problem. The README is upfront about it: Pro 4K output is a big file, and cross-border transfers fail often enough that the author added an OSS (object storage) setting on the website - you edit your token, scroll to the bottom, and pick a CN or US OSS region so the result has a download route that works for you. If your downloads keep dying mid-transfer, that's the fix, not reinstalling anything. Same for the usual suspects: white 4K images and 429/500s are Google load problems (premium group on the site is the real cure), and every prompt and reference you send goes through a reseller's server. Great node; just budget for its file sizes.

Categoryzhenzhen/Google

Inputs (21)

NameTypeDefaultDescription
promptSTRING
image1optIMAGE
image2optIMAGE
image3optIMAGE
image4optIMAGE
image5optIMAGE
image6optIMAGE
image7optIMAGE
image8optIMAGE
api_keyoptSTRING
num_imagesoptINT11–4
aspect_ratiooptCOMBOauto11 options: auto, 21:9, 16:9, 3:2, 4:3, 5:4, +5
resolutionoptCOMBO1K3 options: 1K, 2K, 4K
output_formatoptCOMBOpng3 options: png, jpeg, webp
safety_toleranceoptCOMBO46 options: 1, 2, 3, 4, 5, 6
system_promptoptSTRINGOptional system instruction to steer model persona and output style.
seedoptINT00–655350 = random seed. FAL seed max is 65535.
image_wayoptCOMBOimage_url2 options: image_url, base64
poll_intervaloptINT31–30
max_poll_attemptsoptINT120010–3600Default 1200*3s = 1 hour timeout.
skip_erroroptBOOLEANfalse开启后,节点失败时不报错、返回默认空结果。

Outputs (3)

NameTypeDescription
imagesIMAGE
image_urlsSTRING
responseSTRING