fast yet good image. intended for wainsfw v13, may not work with other checkpoints
Profil d'exécution
Description de la source
fast yet good image. intended for wainsfw v13, may not work with other checkpoints
v2 update:
automatic cfg (less burns and artifact)
cleaner workflow
key improvement:
taesdxl (very fast latent decoding)
controlnet union (used for upscale)
2x upscaler model (instead of 4x)
required models
Commentaire généré par l’IA
Explication générée par l’IA à partir des détails de la source et de la configuration. Les suggestions sont clairement signalées.
WAI-NSFW V13 WORKFLOW is for making images from the wainsfw v13 checkpoint; it uses TAESDXL for latent decoding and xinsir controlnet union with RealESRGAN 2x for upscaling, and it produces an image.
For upscaling, it uses xinsir controlnet union and a 2x upscaler instead of a 4x model.
Named model inputs are wainsfw v13, RealESRGAN 2x, xinsir controlnet union, and TAESDXL; eyeful is optional.
It is listed with Illustrious as its base model.
Before use, verify that the listed model files and node packs are available.
Suggestion · non vérifié
Listed model files are bbox/Eyeful_v2-Individual.pt, bbox/face_yolov8m.pt, diffusion_pytorch_model.safetensors, RealESRGAN_x2.pth, sam_vit_b_01ec64.pth, v2-1_768-ema-pruned.safetensors, and wainsfw.safetensors.
Listed node packs are cg-use-everywhere, ComfyUI_Comfyroll_CustomNodes, comfyui_smznodes, comfyui_tinyterranodes, comfyui-automaticcfg, comfyui-detail-daemon, comfyui-impact-pack, comfyui-impact-subpack, comfyui-inspire-pack, efficiency-nodes-comfyui, and rgthree-comfy.
The v2 update includes Automatic CFG, described as reducing burns and artifacts.
Use the wainsfw v13 checkpoint; the workflow may not work with other checkpoints.
Suggestion · non vérifié
Faut-il modifier cela ?
Connectez-vous pour envoyer une demande de modification.
Sources
1 sourceExtraits de sources
2 extraitsSource context: 6318 downloads · Type Workflows · Base model Illustrious
wainsfw v13
RealESRGAN 2x
xinsir controlnet union
eyeful (optional)
TAESDXL
Remaining hardware or download-size estimates are not available yet.
Exigences
Object Detector · Hugging Face · bbox/Eyeful_v2-Individual.pt · SHA-256 278fee230b1b
Object Detector · Hugging Face · bbox/face_yolov8m.pt
Source context: 6317 downloads · Type Workflows · Base model Illustrious
diffusion_pytorch_model.safetensors
PossibleControlNet · Unknown
Upscaler · 64.0 MB · PTH · Unknown
Segmentation · 358 MB · PTH · Unknown
v2-1_768-ema-pruned.safetensors
Fichier non vérifiéCheckpoint · Hugging Face · stabilityai/stable-diffusion-2-1 · SHA-256 dcd690123cfc
wainsfw.safetensors
Non résoluCheckpoint · Unknown
cg-use-everywhere
TrouvéPack de nœud · Registry
ComfyUI_Comfyroll_CustomNodes
TrouvéPack de nœud · Registry
Pack de nœud · Registry
comfyui_tinyterranodes
TrouvéPack de nœud · Registry
comfyui-automaticcfg
TrouvéPack de nœud · Registry
comfyui-detail-daemon
TrouvéPack de nœud · Registry
comfyui-impact-pack
TrouvéPack de nœud · Registry
comfyui-impact-subpack
TrouvéPack de nœud · Registry
Pack de nœud · Registry
efficiency-nodes-comfyui
TrouvéPack de nœud · Registry
rgthree-comfy
TrouvéPack de nœud · Registry