WorkflowListedExternal

RAMTHRUST DEMIGOD LATENT UPSCALER — SDXL v4.0

HELLO! I am RAMTHRUST and I am pleased to present to you my daily driver workflow.

Sourcecivitai.com/models/449574

TaskMultiCapabilitiesImage edit · Image to image · UpscalingFamilyIllustriousEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Oct 2, 2026

Source description

HELLO! I am RAMTHRUST and I am pleased to present to you my daily driver workflow.

This workflow is something exceptional but VRAM heavy. It's so VRAM heavy that I think you need a MINIMUM of 16GB of VRAM.

It's slow, it's ugly, but godDAMN does it produce high quality images!

There are TONS of notes inside with download links to all of the detailers and other items you'll need to dance with the devil IN SDXL VERSION 1.01.

Basically, the process is as follows:

Get those missing resources, you should know how to do this in comfyui. There are download links in all of the notes for maximum convenience

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

RAMTHRUST DEMIGOD LATENT UPSCALER is a ComfyUI workflow for generating images and upscaling selected results: it starts with native image generation, lets you choose one or more images in Preview Chooser, and is described as producing 2× upscaled images.

Flow

Generate images, select the ones you want to upscale in Preview Chooser, then proceed to the upscale stage.

Inputs and outputs

The creator describes save points for native generation, pass-2 latent upscaling, and the detailer pass, letting you compare those stages without generating again.

Setup

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

Dependencies

Listed ComfyUI node packs include ComfyUI-Advanced-ControlNet, comfy_mtb, ComfyUI_Swwan, ComfyUI-Custom-Scripts, mikey_nodes, ComfyUI-Impact-Subpack, ComfyUI-Impact-Pack, and ComfyUI_Comfyroll_CustomNodes.
Named model files 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 named model files 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.

Configuration

The listing names Illustrious as the base model.
The listing does not specify a license.

Cautions

The creator describes the workflow as VRAM-heavy and estimates it may need at least 16 GB of VRAM; check your available VRAM before use.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimary

civitai.com/models/449574

Verified Jul 20

Source excerpts

1 excerpt

NoteJul 20civitai.com/models/449574

Source context: 1369 downloads · Type Workflows · Base model Illustrious