ComfyUI Node: Nano Banana - Unbiased Face Swap
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
NanoBanana FaceSwap
Inputs
api_key STRING
model
- gemini-3.1-flash-image-preview
- gemini-3-pro-image-preview
- gemini-2.5-flash-image
target_image IMAGE
identity_1 IMAGE
scope
- face
- head
- head+styling
custom_hint STRING
seed INT
batch_axis
- target
- identity
detector
- auto
- mediapipe
- opencv_yunet
- gemini_bbox
mask_dilate_px INT
mask_feather_px INT
image_size
- 1K
- 2K
- 4K
thinking_level
- NONE
- LOW
- MEDIUM
- HIGH
apply_integrate BOOLEAN
lab_strength FLOAT
grain_strength FLOAT
composite_method
- feather
- laplacian
match_directional_lighting BOOLEAN
identity_2 IMAGE
identity_3 IMAGE
identity_4 IMAGE
identity_5 IMAGE
identity_6 IMAGE
dry_run BOOLEAN
timeout_ms INT
ref_cap_px INT
auto_relax_on_refused BOOLEAN
network NB_NETWORK
Outputs
IMAGE
STRING
MASK
IMAGE
Extension: NanoBanana FaceSwap
Face/head replacement for ComfyUI via Google Nano Banana 2 (Gemini image editing). Five swap pathways (whole, crop, mask-inpaint, unbiased, painted-edit), mediapipe + YuNet + Gemini bbox detector cascade, LAB / grain / sharpness / Laplacian compositing, identity-ref obfuscation for celebrity-classifier evasion.
Authored by IxMxAMAR
Looking for a different node?
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.