WorkflowListedExternal

t2i2i

My first at attempt at sharing on here. Would like feedback on my workflow.

Sourcecivitai.com/models/2077431

TaskMultiCapabilitiesImage edit · Text to image · UpscalingFamilyIllustriousEstimated VRAMEstimate unavailableBgrade

Runtime profile

Access: External workflow
Status: Listed
Source: Civitai
Updated: Jul 19, 2026

Source description

My first at attempt at sharing on here. Would like feedback on my workflow.

Starting checkpoint loader is where the t2i happens. The one labeled as Refiner is what's used to convert the generated image to another image. It's okay at converting anime/non realistic to realistic as is. But you can use whatever two checkpoints you want.

Estimated VRAM requirement

Estimate unavailable

224 MB across 2 of 9 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.

Requirements

AI-generated commentary

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

Purpose

t2i2i uses one checkpoint to generate an initial image, then uses a second checkpoint labeled Refiner to convert that image into another image. Its meaningful inputs are the two checkpoints, and its outputs are the generated image and the converted image.

Flow

The starting checkpoint loader performs the text-to-image step, followed by the Refiner conversion.

Inputs and outputs

The Refiner is described as converting the generated image into another image.

Setup

Find t2i2i at https://civitai.com/models/2077431.
The listing identifies Delta45424155 as the publisher and Illustrious as the base model.

Dependencies

The listed node-pack names are: comfyui-easy-use, rgthree-comfy, comfyui_ultimatesdupscale, comfyui-impact-pack, comfyui-impact-subpack, ComfyUI_Comfyroll_CustomNodes, and comfyui_controlnet_aux.
The listed model files include 4x_foolhardy_Remacri.pth, illustriousXLV10_v10.safetensors, mysterystew_v10.safetensors, and ultraUniversalis16_v10.safetensors.
Other listed files are Anzhcs%20WomanFace%20v05%201024%20y8n.pt, sam_vit_b_01ec64.pth, xinsirUnion-sdxl-promax.safetensors, and illustriousXLLineart_v10.safetensors.

Configuration

Choose any two checkpoints: assign one to the starting text-to-image step and one to the Refiner step.
Suggestion · not verified
A stated Refiner use case is converting anime or non-realistic images to realistic images.

Cautions

Before using the workflow, confirm that all listed model files are available in your setup.
Suggestion · not verified
Before setup, verify which exact package you plan to use for comfyui_controlnet_aux.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiPrimaryVersion 2350642

civitai.com/models/2077431

Verified Jul 19

Source excerpts

1 excerpt

NoteJul 19civitai.com/models/2077431

Source context: 129 downloads · Type Workflows · Base model Illustrious