RAMTHRUST DEMIGOD LATENT UPSCALER

RAMTHRUST DEMIGOD LATENT UPSCALER is a ComfyUI workflow for generating images and upscaling selected results; its described input is a generated image, and its intended final output is a 2× upscaled image.

Generate images, choose one or more in Preview Chooser, then proceed to upscale them.

Save points are provided for native generation, pass-2 latent upscaling, and the detailer pass, so you can compare those stages without generating again.

The creator says the notes include download links for detailers and other items for SDXL version 1.01.

Model files named include 1x-ITF-SkinDiffDetail-Lite-v1.pth; 4x-UltraSharp.pth; bbox/breasts_seg.pt; bbox/Eyeful_v2-Individual.pt; bbox/face_yolov8m.pt; bbox/hand_yolov8s.pt; and diffusers_xl_canny_full.safetensors.

Other model files named include diffusers_xl_depth_full.safetensors; Illustrious-Black-Magic-Clean27.safetensors; kohya_controllllite_xl_openpose_anime.safetensors; sdxl_vae.safetensors; segm/deepfashion2_yolov8s-seg.pt; segm/hair_yolov8n-seg_60.pt; and segm/skin_yolov8m-seg_400;

Listed required ComfyUI packs are ComfyUI-Advanced-ControlNet, comfy_mtb, ComfyUI_Swwan, ComfyUI-Custom-Scripts, mikey_nodes, ComfyUI-Impact-Subpack, ComfyUI-Impact-Pack, and ComfyUI_Comfyroll_CustomNodes.

The listed base model is Illustrious, and the workflow is published by RAMTHRUST.

The listing does not specify a license for this workflow.

The creator describes the workflow as VRAM-heavy and slow and estimates a minimum of 16 GB of VRAM; check your hardware against that estimate before use.

Sugestão · não verificado