Img2img+face detailer workflow(Flux/Illustrious),and you can compare the result before/after the face refine. I tested with several checkpoints,this workflow fits better with:
Laufzeitprofil
Quellenbeschreibung
Img2img+face detailer workflow(Flux/Illustrious),and you can compare the result before/after the face refine. I tested with several checkpoints,this workflow fits better with:
For flux dev version: Edge of Reality 真实边缘 - 3.2 Beyond Reality | Flux Checkpoint | Civitai
For illustrious version:
Vauxz Merge 2.5D - 3D - ILLU v.Sarah | Illustrious Checkpoint | Civitai
Remaining hardware or download-size estimates are not available yet.
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
This workflow is for image-to-image face refinement: it takes an image, applies face detailing, and can produce a refined image plus a before-and-after comparison for Flux or Illustrious.
Its graph includes nodes for loading an image, encoding and decoding, sampling, face detailing, image comparison, and saving an output.
Input: an image for image-to-image processing. Outputs: a face-refined image and a before-and-after comparison.
The listed base model is Illustrious.
It lists these node packs: ComfyUI-GGUF, comfyui-impact-pack, comfyui-impact-subpack, and rgthree-comfy.
It lists these model files: bbox/face_yolov8m.pt, clip_l.safetensors, edgeOfReality_32BeyondReality.safetensors, and flux_ae.safetensors.
It also lists realDream_flux1V1GGUFQ4KM.gguf, sam_vit_b_01ec64.pth, t5xxl_fp8_e4m3fn.safetensors, and vauxzMerge25D3D_illuVSarah.safetensors.
For Flux dev, consider Edge of Reality 真实边缘 - 3.2 Beyond Reality; for Illustrious, consider Vauxz Merge 2.5D - 3D - ILLU v.Sarah.
Vorschlag · nicht geprüft
Before running, verify that the eight listed model files are available under their exact filenames.
Vorschlag · nicht geprüft
Before running, verify which ComfyUI-GGUF package matches your setup.
Vorschlag · nicht geprüft
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
1 AuszugSource context: 1357 downloads · Type Workflows · Base model Illustrious
Anforderungen
Object Detector · Hugging Face · bbox/face_yolov8m.pt
clip_l.safetensors
MöglichText encoder · Unknown
Checkpoint · 11.1 GB · SAFETENSORS · fp8 · Unknown
flux_ae.safetensors
Nicht aufgelöstVAE · Unknown
realDream_flux1V1GGUFQ4KM.gguf
Nicht aufgelöstCheckpoint · Unknown
Segmentation · 358 MB · PTH · Unknown
Text encoder · Unknown · SHA-256 7d330da48161
vauxzMerge25D3D_illuVSarah.safetensors
Nicht aufgelöstCheckpoint · Unknown
ComfyUI-GGUF
MöglichKnotenpaket · Registry
comfyui-impact-pack
GefundenKnotenpaket · Registry
comfyui-impact-subpack
GefundenKnotenpaket · Registry
rgthree-comfy
Knotenpaket · Registry