fast yet good image. intended for wainsfw v13, may not work with other checkpoints
Perfil de ejecución
Descripción de la fuente
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
Comentario generado por IA
Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.
WAI-NSFW V13 WORKFLOW is for generating images with the wainsfw v13 checkpoint; it uses RealESRGAN 2x, xinsir controlnet union, and TAESDXL, with eyeful optional, and produces an image that can be upscaled with ControlNet Union and a 2x upscaler.
The workflow uses TAESDXL for latent decoding, then uses ControlNet Union with a 2x upscaler model for upscale instead of a 4x model.
Named inputs are wainsfw v13, RealESRGAN 2x, xinsir controlnet union, and TAESDXL; eyeful is optional.
The described output is an image, with ControlNet Union identified for upscale.
Before use, check that the listed model files and node packs are available.
Sugerencia · sin verificar
Named 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.
Named 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.
Version 2 includes Automatic CFG, described as producing fewer burns and artifacts.
For upscale, use ControlNet Union with the 2x upscaler model specified in the description.
Sugerencia · sin verificar
Use wainsfw v13 as the checkpoint; the description says the workflow may not work with other checkpoints.
Sugerencia · sin verificar
Verify the exact file names before use, including wainsfw.safetensors, RealESRGAN_x2.pth, diffusion_pytorch_model.safetensors, and the bbox and segmentation files listed above.
Sugerencia · sin verificar
¿Es necesario editarlo?
Inicia sesión para solicitar una edición.
Fuentes
1 fuenteExtractos de fuentes
2 extractosSource context: 6318 downloads · Type Workflows · Base model Illustrious
wainsfw v13
RealESRGAN 2x
xinsir controlnet union
eyeful (optional)
TAESDXL
Requisito de VRAM estimado
Estimación no disponible
Los tamaños de los modelos aún no están lo bastante completos para calcular este requisito.
Requisitos
18 requisitosObject Detector · Hugging Face · bbox/Eyeful_v2-Individual.pt
Object Detector · Hugging Face · bbox/face_yolov8m.pt
diffusion_pytorch_model.safetensors
PosibleControlNet · Unknown
RealESRGAN_x2.pth
ConflictoUpscaler · Unknown
sam_vit_b_01ec64.pth
ConflictoSegmentation · Unknown
v2-1_768-ema-pruned.safetensors
ConflictoCheckpoint · Hugging Face · stabilityai/stable-diffusion-2-1
wainsfw.safetensors
No resueltoCheckpoint · Unknown
Paquete de nodos · Registry
Paquete de nodos · Registry
Source context: 6317 downloads · Type Workflows · Base model Illustrious
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry