ComfyUI Node
Ultimate Face Fix
Detects, reconstructs, semantically masks, and seamlessly blends one or many faces.
Ultimate Face Fix
- image
- model
- vae
- positive
- negative
- face_detector
- face_landmarker
- bboxes
- face_parser
- sam_model
- fixed_image
- original_face_crops
- processed_face_crops
- face_mask
- debug_preview
◄face_selectionall►
◄detection_qualitymaximum►
◄max_faces16►
◄min_face_size24►
◄detection_confidence0.25►
◄context_scale1.80►
◄target_resolution1024►
◄repair_modecustom►
◄custom_denoise0.40►
◄seed0►
◄steps25►
◄cfg5.5►
◄sampler_nameeuler►
◄schedulerbeta►
◄mask_presetcore_face►
◄sam_refineauto►
◄mask_grow_percent1.5►
◄mask_feather_percent2.5►
◄color_match_strength0.65►
◄blend_modemultiband►
Categoryultimate face fix
Inputs (30)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | — | |
| model | MODEL | Generation model used for crop img2img. | |
| vae | VAE | — | |
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| face_selection | COMBO | all | 3 options: all, largest, largest_n |
| detection_quality | COMBO | maximum | 2 options: maximum, balanced |
| max_faces | INT | 161–64 | — |
| min_face_size | INT | 244–1024 | — |
| detection_confidence | FLOAT | 0.250.01–1 | — |
| context_scale | FLOAT | 1.801.1–3 | — |
| target_resolution | COMBO | 1024 | 5 options: none, 512, 768, 1024, 1536 |
| repair_mode | COMBO | custom | 4 options: detail, repair, reconstruct, custom |
| custom_denoise | FLOAT | 0.400–1 | — |
| seed | INT | 00–18446744073709550000 | — |
| steps | INT | 251–200 | — |
| cfg | FLOAT | 5.50–100 | — |
| sampler_name | COMBO | euler | 44 options: euler, euler_cfg_pp, euler_ancestral, euler_ancestral_cfg_pp, heun, heunpp2, +38 |
| scheduler | COMBO | beta | 9 options: simple, sgm_uniform, karras, exponential, ddim_uniform, beta, +3 |
| mask_preset | COMBO | core_face | 3 options: core_face, portrait_safe, head |
| sam_refine | COMBO | auto | 3 options: auto, always, off |
| mask_grow_percent | FLOAT | 1.50–15 | — |
| mask_feather_percent | FLOAT | 2.50–15 | — |
| color_match_strength | FLOAT | 0.650–1 | — |
| blend_mode | COMBO | multiband | 2 options: multiband, alpha |
| face_detectoropt | FACE_FIX_DETECTOR | Connect Load Face Fix Detector. It may be omitted only when bboxes is connected. | |
| face_landmarkeropt | FACE_DETECTION_MODEL | Connect ComfyUI's Load Face Detection Model (MediaPipe) output for landmark-aware crops. | |
| bboxesopt | BOUNDING_BOX | [object Object] | When connected, these boxes replace YOLO detection. |
| face_parseropt | FACE_FIX_PARSER | Connect Load Face Fix Parser. When omitted, SAM/landmark/geometry fallback masks are used. | |
| sam_modelopt | MODEL | Connect the MODEL output from the supplied SAM 3.1 checkpoint. |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| fixed_image | IMAGE | — |
| original_face_crops | IMAGE | — |
| processed_face_crops | IMAGE | — |
| face_mask | MASK | — |
| debug_preview | IMAGE | — |