This is the version for Anima, I really liked it.
Laufzeitprofil
Quellenbeschreibung
V1.3 - Anima:
V1.2:
Some people have asked me to share my character workflow.
Why not?
So I refined it and added a randomizer, enjoy!
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
This Anima v1.3 workflow is for generating detailed full-body characters and includes a randomizer, ControlNet, and frame control; it uses the Anima base model plus listed model files and node packs, while its exact input fields and output format are not stated.
It requires model files and node packs, including anima-lllite-inpainting-v2.safetensors, sam3.1_multiplex_fp16.safetensors, comfyui-kjnodes, and rgthree-comfy.
It is built around the Anima base model and also lists model files and node packs; specific input fields are not stated.
The stated task output is a detailed full-body character; the exact output format is not stated.
Verify the input fields and output format before use.
Vorschlag · nicht geprüft
Open Anima v1.3 at https://civitai.com/models/2098929?modelVersionId=2959226; the listing names Anima as the base model and Slavikson as publisher.
No license is specified for this workflow.
Listed model files include anima_baseV10.safetensors, anima-lllite-inpainting-v2.safetensors, qwen_3_06b_base.safetensors, and qwen_image_vae.safetensors.
Additional listed model files are sam3.1_multiplex_fp16.safetensors, sam_vit_b_01ec64.pth, segm/person_yolov8m-seg.pt, bbox/hand_yolov8s.pt, and Face YOLO v3.pt.
The listed node packs are comfyui_essentials, comfyui-impact-pack, comfyui-impact-subpack, comfyui-kjnodes, rgthree-comfy, was-node-suite-comfyui, and was-ns.
Frame control was added to help prevent the character from moving out of the frame.
ControlNet was added in v1.2, and the workflow was refined with a randomizer.
The description warns that the method does not work well with V-Pred models.
Before use, verify these model files and node packs against your installation: qwen_3_06b_base.safetensors, qwen_image_vae.safetensors, anima_baseV10.safetensors, segm/person_yolov8m-seg.pt, bbox/hand_yolov8s.pt, sam_vit_b_01ec64.pth, Face YOLO v3.pt, was-node-suite-comfyui, and
Vorschlag · nicht geprüft
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
3 AuszügeSource context: 2416 downloads · Type Workflows · Base model Anima
WARNING! This method does not work well with V-Pred models.
Geschätzter VRAM Bedarf
Schätzung nicht verfügbar
673 MB über 4 von 9 Modell-Dateien. Gesamtmodell-Dateien + 25% Ladeaufwand + 2 GB Ausführungs-Puffer, aufgerundet.
Anforderungen
16 AnforderungenCheckpoint · Civitai · 2458426
Mögliche Quellen
anima-lllite-inpainting-v2.safetensors
Datei ungeprüftControlNet · SAFETENSORS · Unknown
Object Detector · 21.5 MB · Hugging Face · Bingsu/adetailer
Face YOLO v3.pt
Nicht aufgelöstObject Detector · Unknown
Text encoder · Civitai · 2695493
Mögliche Quellen
VAE · 242 MB · Civitai · 1842123
Mögliche Quellen
Segmentation · 358 MB · Hugging Face · comfyuistudio/sam_vit_b_01ec64.pth
sam3.1_multiplex_fp16.safetensors
Datei ungeprüftVision model · SAFETENSORS · Unknown
Object Detector · 52.3 MB · Hugging Face · Bingsu/adetailer
Knotenpaket · Registry
Knotenpaket · Registry
Source context: 2269 downloads · Type Workflows · Base model Anima
Source context: 2268 downloads · Type Workflows · Base model Anima
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
was-node-suite-comfyui
MöglichKnotenpaket · Registry
was-ns
Nicht aufgelöstKnotenpaket · Registry