Skip to content
WorkflowListedExternal
Open source

FLUX - text2img + upscale workflow for beginner (2 option included) — v1.0

This workflow is designed for use with ComfyUI and allows users to generate images from text using FLUX's text-to-image (t2i) capabilities and upscale them immediately.

Sourcecivitai.com/models/993938
TaskMultiCapabilitiesText to image · UpscalingFamilyFLUXEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Source
Civitai
Updated
Sep 1, 2026

Source description

This workflow is designed for use with ComfyUI and allows users to generate images from text using FLUX's text-to-image (t2i) capabilities and upscale them immediately.

It is structured in sequential phases to ensure ease of understanding, especially for beginners.

The workflow offers two options

Option 1: Proceed directly from image generation to upscaling using the same prompt.

Option 2: Use different prompts for image generation and upscaling, allowing for more customization.

==============================================================

이 워크플로우는 ComfyUI에서 사용하도록 설계되었으며, FLUX의 텍스트-이미지(t2i) 기능을 사용하여 텍스트로부터 이미지를 생성하고 즉시 업스케일할 수 있습니다.

초보자도 쉽게 이해할 수 있도록 순차적인 단계로 구성되어 있습니다.

업스케일 시 두 가지 옵션이 있습니다.

옵션 1: 동일한 프롬프트를 사용하여 이미지 생성 후 바로 업스케일 진행.

옵션 2: 이미지 생성과 업스케일 시 다른 프롬프트를 사용하여 보다 맞춤화된 결과를 얻을 수 있음.

[contact]

Youtube : https://www.youtube.com/@A01demort

Instagram : https://www.instagram.com/a01demort/

Naver Cafe : https://cafe.naver.com/sdfkorea

sdhotline : https://sdhotline.com/

What you need

Model files
21.2 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requirements

Models

12

  • 1xSkinContrast-HighAlternative-SuperUltraCompact.pth

    Not resolved

    Upscaler · Unknown

  • clip_l.safetensors

    Found

    Text encoder · 235 MB · SAFETENSORS · Unknown

  • DualCLIPLoader

    Possible

    Text encoder · Unknown

  • FLUX_VAE_diffusion_pytorch_model.safetensors

    Not resolved

    VAE · Unknown

  • flux1-dev-Q8_0.gguf

    Found

    Checkpoint · 11.8 GB · GGUF · fp16 · Unknown

  • flux1DevFp8_v10.safetensors

    Not resolved

    Checkpoint · Unknown

  • remacri_original.pth

    Not resolved

    Upscaler · Unknown

  • t5xxl_fp16.safetensors

    Found

    Text encoder · 9.12 GB · SAFETENSORS · Unknown

  • UltimateSDUpscale

    Possible

    Upscaler · Unknown

  • UpscaleModelLoader

    Possible

    Upscaler · Unknown

  • VAEDecode

    Possible

    VAE · Unknown

  • VAELoader

    Possible

    VAE · Unknown

Node packs

8

  • CLIPTextEncodeFlux

    Not resolved

    Node pack · Unknown

  • EmptyLatentImage

    Possible

    Node pack · Unknown

  • Image Comparer (rgthree)

    Not resolved

    Node pack · Unknown

  • KSampler

    Possible

    Node pack · Unknown

  • PreviewImage

    Possible

    Node pack · Unknown

  • SaveImage

    Possible

    Node pack · Unknown

  • UNETLoader

    Possible

    Node pack · Unknown

  • UnetLoaderGGUF

    Possible

    Node pack · Unknown

AI-generated commentary

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

Purpose

  • Use this ComfyUI workflow to turn a text prompt into a FLUX image and an upscaled version; for upscaling, reuse the prompt or enter a different one.

Flow

  • The workflow runs in sequential phases: image generation followed by upscaling.

Inputs and outputs

  • Input a text prompt; the outputs are the generated image and its upscaled version.

Setup

  • The workflow is designed for ComfyUI and lists Flux.1 D as its base model.

Dependencies

  • Listed model files are: 1xSkinContrast-HighAlternative-SuperUltraCompact.pth, clip_l.safetensors, FLUX_VAE_diffusion_pytorch_model.safetensors, flux1-dev-Q8_0.gguf, flux1DevFp8_v10.safetensors, remacri_original.pth, and t5xxl_fp16.safetensors.

  • Named node types include CLIPTextEncodeFlux, DualCLIPLoader, EmptyLatentImage, Image Comparer (rgthree), KSampler, PreviewImage, SaveImage, UltimateSDUpscale, UNETLoader, UnetLoaderGGUF, UpscaleModelLoader, VAEDecode, and VAELoader.

Configuration

  • For upscaling, choose the prompt used for image generation or provide a different prompt.

Cautions

  • The listing does not specify a license; check the usage terms before reuse.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimary
civitai.com/models/993938

Verified Jul 20

Source excerpts

1 excerpt
NoteJul 20civitai.com/models/993938

Source context: 902 downloads · Type Workflows · Base model Flux.1 D