WorkflowListedExternal

Simple Text2Image Workflow for Beginners — v1.1

For those just starting out who want a simple workflow to generate large high-quality images with detailed faces. Plus, when generating larger batches, you save some time by choosing which pictures are greenlit to go...

Sourcecivitai.com/models/1624512

TaskUpscalingFamilyIllustriousVersionRelease 1838612 — simpleText2Image_v1_1.jsonEstimated VRAMEstimate unavailableDgrade

Runtime profile

Access: External workflow
Status: Listed
Version: simpleText2Image_v1_1.json
Source: Civitai
Updated: Jul 20, 2026

Source description

I'm pretty new to ComfyUI myself, so I know how confusing most of the "Simple Workflows" are, so I really did my best to simplify this to what I think are base essentials to start getting good pictures. Just download the missing nodes and use the upscaler and VAE of your choice. If you're not sure, just search for the ones I'm using, they've worked pretty well for me so far.

V1.1

The anything everywhere nodes seemed to not work when loading the workflow, so I uploaded a version without them. It's less neat, but does all the same things.

AI-generated commentary

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

Purpose

Simple Text2Image Workflow for Beginners — v1.1 is a ComfyUI workflow for generating large images with detailed faces from prompts, styling, checkpoints, VAEs, and LoRAs, then selecting images for face detailing, upscaling, and comparison.

Flow

The workflow includes image generation, image filtering for refinement and upscaling, face detailing, an upscaler, and image comparisons.

Inputs and outputs

Inputs include a prompt and styling controls, a checkpoint, a VAE, multiple LoRA loaders, and basic render settings.
Outputs include generated images, images selected for refinement and upscaling, and image comparisons.

Setup

Download missing nodes and choose the upscaler and VAE you want to use.
Suggestion · not verified

Dependencies

The listed node packs are all-in-one-style, cg-image-filter, ComfyLiterals, comfyui_ultimatesdupscale, comfyui-art-venture, comfyui-impact-pack, comfyui-impact-subpack, and rgthree-comfy.
It lists bbox/face_yolov8n_v2.pt as an object detector.
It also lists RealESRGAN_x4plus_anime_6B.pth as an upscaler and waiNSFWIllustrious_v140.safetensors as a checkpoint.

Configuration

Available components cover prompt and styling, checkpoint, VAE and LoRA loading, basic render settings, image filtering, face detailing, upscaling, and image comparisons.
For larger batches, select which images should go through face detailing and upscaling with the image filter.
Suggestion · not verified
Illustrious is the listed base model, and this release is v1.1.

Cautions

RealESRGAN_x4plus_anime_6B.pth and waiNSFWIllustrious_v140.safetensors are identified by filename only, so verify the exact files before use.
Suggestion · not verified
Version v1.1 omits the anything everywhere nodes after they seemed not to work when loading; check your node setup if those nodes matter to you.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiSourceVersion 1838612

civitai.com/models/1624512

Verified Aug 4

Source excerpts

1 excerpt

NoteAug 4civitai.com/models/1624512

Source context: 872 downloads · Type Workflows · Base model Illustrious