A 4 stage workflow (1) generating a base image using a different base model (the model I used can be found in the version description), (2) refining the image with Z-Image-Turbo to add realism to the image, (3)...
Laufzeitprofil
Quellenbeschreibung
A 4 stage workflow (1) generating a base image using a different base model (the model I used can be found in the version description), (2) refining the image with Z-Image-Turbo to add realism to the image, (3) detailing the image using detailer subgroups, and (4) upscaling and refining the image.
The final step in stage 4 (enhance and sharpen) requires the ImageMagick binaries to be installed. They are available for download here: https://imagemagick.org/script/download.php .
Geschätzter VRAM Bedarf
Schätzung nicht verfügbar
11,9 GB über 3 von 8 Modell-Dateien. Gesamtmodell-Dateien + 25% Ladeaufwand + 2 GB Ausführungs-Puffer, aufgerundet.
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
Use ZIT Refiner workflows - SDXL v1 to generate and refine images. It uses a different base model to create a starting image, adds realism with Z-Image-Turbo and detail with detailer subgroups, then produces an upscaled, refined image.
The first stage uses a different base model to generate the starting image; the final stage produces an upscaled, refined image.
The final enhance-and-sharpen step in stage 4 requires ImageMagick binaries, available at https://imagemagick.org/script/download.php.
Listed model files: 4x-UltraSharpV2.safetensors, ae.safetensors, bbox/Eyes.pt, bbox/face_yolov9c.pt, intorealismUltra_v80.safetensors, qwen_3_4b.safetensors, sam_vit_b_01ec64.pth, and z_image_turbo_bf16.safetensors.
Listed node packs: cg-use-everywhere, comfy-image-saver, ComfyUI_Comfyroll_CustomNodes, comfyui-impact-pack, comfyui-impact-subpack, comfyui-magickwand, rgthree-comfy, and was-ns.
The listing identifies SDXL 1.0 as the base model.
Check the version description to identify the different base model used in stage 1.
Vorschlag · nicht geprüft
Before use, check that the listed model files and node packs are available in your setup.
Vorschlag · nicht geprüft
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
1 AuszugSource context: 747 downloads · Type Workflows · Base model SDXL 1.0
Anforderungen
16 AnforderungenUpscaler · 133 MB · SAFETENSORS · Unknown
ae.safetensors
GefundenVAE · 320 MB · SAFETENSORS · Unknown
Object Detector · Hugging Face · bbox/Eyes.pt
Object Detector · Hugging Face · bbox/face_yolov9c.pt
intorealismUltra_v80.safetensors
Nicht aufgelöstCheckpoint · Unknown
Text encoder · Unknown · Z Image Turbo (Turbo)
sam_vit_b_01ec64.pth
Nicht aufgelöstSegmentation · Unknown
z_image_turbo_bf16.safetensors
GefundenCheckpoint · 11.5 GB · SAFETENSORS · bf16 · Unknown
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
was-ns
Nicht aufgelöstKnotenpaket · Registry