ComfyUI Node
Person Detailer
Per-person face/body detailing with individual LoRA and prompt per reference slot. Connect PERSON_DATA from Person Selector Multi to assign faces to slots. Each enabled slot inpaints its matched region using the slot's LoRA and prompt. The generic slot handles unmatched faces via connected components. Mask type per slot (via Inpaint Options): - face/head/body/hair/etc: use pre-computed masks from Person Selector Multi - aux: use body-part SEGS from detector (connect SEGS or detector input) For both head + body-part detailing, chain two PersonDetailer nodes. Optional inputs: - positive_base: fallback conditioning when a slot's prompt is empty - negative: negative conditioning (empty if not connected) - dd_options: Detail Daemon fine-tuning from Detail Daemon Options node - inpaint_options: advanced inpaint settings from Inpaint Options node
Person Detailer
- images
- person_data
- model
- clip
- vae
- positive_base
- negative
- dd_options
- inpaint_options
- images
- refined
- refined_references
- refined_generic
◄seed0►
◄steps4►
◄denoise0.52►
◄sampler_name▾►
◄scheduler▾►
◄detail_daemon_enabledtrue►
◄detail_amount0.20►
◄dd_smoothtrue►
◄mask_blend_pixels32►
◄mask_expand_pixels0►
◄target_width800►
◄target_height1200►
◄reference_1_enabledtrue►
◄reference_1_lora▾►
◄reference_1_lora_strength1.00►
◄reference_1_prompt►
◄reference_2_enabledfalse►
◄reference_2_lora▾►
◄reference_2_lora_strength1.00►
◄reference_2_prompt►
◄reference_3_enabledfalse►
◄reference_3_lora▾►
◄reference_3_lora_strength1.00►
◄reference_3_prompt►
◄reference_4_enabledfalse►
◄reference_4_lora▾►
◄reference_4_lora_strength1.00►
◄reference_4_prompt►
◄reference_5_enabledfalse►
◄reference_5_lora▾►
◄reference_5_lora_strength1.00►
◄reference_5_prompt►
◄generic_enabledfalse►
◄generic_catch_unprocessedtrue►
◄generic_lora▾►
◄generic_lora_strength1.00►
◄generic_prompt►
CategoryFVM Tools/Face
Inputs (46)
| Name | Type | Default | Description |
|---|---|---|---|
| images | IMAGE | Input image batch [B, H, W, C] | |
| person_data | PERSON_DATA | Person data from Person Selector Multi node | |
| model | MODEL | Base model (LoRAs are applied as temporary clones per slot) | |
| clip | CLIP | CLIP model for prompt encoding | |
| vae | VAE | VAE for encode/decode in the inpaint pipeline | |
| seed | INT | 00–18446744073709550000 | Global seed, fixed across all slots and batch items |
| steps | INT | 41–100 | Number of sampling steps per inpaint |
| denoise | FLOAT | 0.520–1 | Denoise strength for inpainting (lower = more original detail preserved) |
| sampler_name | COMBO | Sampler algorithm | |
| scheduler | COMBO | Noise schedule | |
| detail_daemon_enabled | BOOLEAN | true | Enable Detail Daemon sigma manipulation for enhanced detail preservation |
| detail_amount | FLOAT | 0.20-5–5 | Detail Daemon strength. Positive = more detail, negative = smoother. 0 = off. |
| dd_smooth | BOOLEAN | true | Smooth the Detail Daemon sigma curve to avoid artifacts |
| mask_blend_pixels | INT | 320–128 | Gaussian feather radius at mask edges for seamless blending |
| mask_expand_pixels | INT | 00–64 | Dilate/expand mask by this many pixels before inpainting |
| target_width | INT | 80064–4096 | Width to resize face crops to before sampling |
| target_height | INT | 120064–4096 | Height to resize face crops to before sampling |
| reference_1_enabled | BOOLEAN | true | Enable reference slot 1 for detailing |
| reference_1_lora | COMBO | LoRA to apply when detailing reference 1 | |
| reference_1_lora_strength | FLOAT | 1.000–2 | LoRA strength for reference 1 |
| reference_1_prompt | STRING | Positive prompt for reference 1. If empty, uses base conditioning. | |
| reference_2_enabled | BOOLEAN | false | Enable reference slot 2 for detailing |
| reference_2_lora | COMBO | LoRA to apply when detailing reference 2 | |
| reference_2_lora_strength | FLOAT | 1.000–2 | LoRA strength for reference 2 |
| reference_2_prompt | STRING | Positive prompt for reference 2. If empty, uses base conditioning. | |
| reference_3_enabled | BOOLEAN | false | Enable reference slot 3 for detailing |
| reference_3_lora | COMBO | LoRA to apply when detailing reference 3 | |
| reference_3_lora_strength | FLOAT | 1.000–2 | LoRA strength for reference 3 |
| reference_3_prompt | STRING | Positive prompt for reference 3. If empty, uses base conditioning. | |
| reference_4_enabled | BOOLEAN | false | Enable reference slot 4 for detailing |
| reference_4_lora | COMBO | LoRA to apply when detailing reference 4 | |
| reference_4_lora_strength | FLOAT | 1.000–2 | LoRA strength for reference 4 |
| reference_4_prompt | STRING | Positive prompt for reference 4. If empty, uses base conditioning. | |
| reference_5_enabled | BOOLEAN | false | Enable reference slot 5 for detailing |
| reference_5_lora | COMBO | LoRA to apply when detailing reference 5 | |
| reference_5_lora_strength | FLOAT | 1.000–2 | LoRA strength for reference 5 |
| reference_5_prompt | STRING | Positive prompt for reference 5. If empty, uses base conditioning. | |
| generic_enabled | BOOLEAN | false | Enable detailing for unmatched faces (not assigned to any reference) |
| generic_catch_unprocessed | BOOLEAN | true | ON: detail all faces not processed by active slots (including matched but disabled slots). OFF: only truly unmatched faces from Person Selector Multi. |
| generic_lora | COMBO | LoRA to apply for unmatched faces | |
| generic_lora_strength | FLOAT | 1.000–2 | LoRA strength for unmatched faces |
| generic_prompt | STRING | Positive prompt for unmatched faces. If empty, uses base conditioning. | |
| positive_baseopt | CONDITIONING | Base positive conditioning, used as fallback when a slot's prompt is empty | |
| negativeopt | CONDITIONING | Negative conditioning. If not connected, an empty negative is used. | |
| dd_optionsopt | DD_OPTIONS | Advanced Detail Daemon parameters from Detail Daemon Options node | |
| inpaint_optionsopt | INPAINT_OPTIONS | Advanced inpaint settings and per-slot overrides from Inpaint Options node |
Outputs (4)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| refined | IMAGE | — |
| refined_references | IMAGE | — |
| refined_generic | IMAGE | — |