Skip to content
WorkflowListedExternal
Open source

Atomix GGUF txt2img workflow — v2.0

Calling Lora in the prompt instead of node.

Sourcecivitai.com/models/676754
TaskMultiCapabilitiesText to image · UpscalingFamilyFLUXVersionRelease 990626 — Atomix Flux GGUF txt2img Workflow V2.jsonEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
Atomix Flux GGUF txt2img Workflow V2.json
Source
Civitai
Updated
Oct 18, 2026

Source description

Atomix GGUF txt2img workflow

Feature

Calling Lora in the prompt instead of node.

The image generation data contain the using model,Lora,embedding information.

Automatically adjust the size of the upscale tile and provide multiple aspect ratio presets.

Integrated with UltimateUpscale and able to switch different models for upscaling.

Integrated with FaceDetailer and able to switch different models for FaceDetailer.

Showing the time consumed by each node and compare it with the previous execution.

Showing FaceDetailer before/after comparison.

How To Use

1.This is a ComfyUI workflow,only for ComfyUI,so make sure that you ComfyUI is available. https://github.com/comfyanonymous/ComfyUI

2.Drag the JSON or PNG files from the zip file to the ComfyUI interface. If everything goes well, the workflow is ready to go.

3.In the step2, there may be a alert for missing nodes, and you need to install these nodes. If you do not want to manually install them, there is a ComfyUI plugin that you must have: ComfyUI Manager https://github.com/ltdrdata/ComfyUI-Manager After installing this plugin, there is an automatic installation function for missing nodes in its management interface.

What you need

Model files
21 GiB known subtotal

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

Requirements

Models

6

  • 8x_NMKD-Superscale_150000_G.pth

    Not resolved

    Upscaler · Unknown

  • Atomix XL V4.safetensors

    Not resolved

    Checkpoint · Unknown

  • bbox/face_yolov8n_v2.pt

    Not resolved

    Object Detector · Hugging Face

  • clip_l.safetensors

    Possible

    Text encoder · Unknown

  • flux1-dev-Q8_0.gguf

    Found

    Checkpoint · 11.8 GB · GGUF · fp16 · Unknown

  • t5xxl_fp16.safetensors

    Found

    Text encoder · 9.12 GB · SAFETENSORS · Unknown

AI-generated commentary

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

Purpose

  • Atomix GGUF txt2img workflow is for creating images from text in ComfyUI: it takes a text prompt with model, LoRA, and embedding information, supports upscaling, and outputs generated images through PreviewImage and SaveImage components.

Flow

  • Specify LoRA in the prompt rather than in a separate node.

  • Choose among aspect-ratio presets, automatically adjust upscale tile size, switch upscaling and FaceDetailer models, and view FaceDetailer before-and-after comparisons.

  • The description includes per-node time reporting and comparison with a previous execution.

Inputs and outputs

  • Input: a text prompt plus the model, LoRA, and embedding information used for image generation.

  • Output: generated images can be previewed and saved through the named PreviewImage and SaveImage components.

Setup

  • Use it in ComfyUI by dragging a JSON or PNG workflow file from the zip archive into the interface.

    Suggestion · not verified

  • If nodes are missing, install them; the description says ComfyUI Manager can provide automatic installation through its management interface.

    Suggestion · not verified

Dependencies

  • Listed model files: 8x_NMKD-Superscale_150000_G.pth; Atomix XL V4.safetensors; bbox/face_yolov8n_v2.pt; clip_l.safetensors; flux1-dev-Q8_0.gguf; and t5xxl_fp16.safetensors.

  • Listed components: Checkpoint Loader with Name (Image Saver); CLIPTextEncode; CR Aspect Ratio; DualCLIPLoader; FaceDetailer; Float Literal (Image Saver); FluxGuidance; Get resolution [Crystools]; Image Comparer (rgthree); Image Saver; ImageScaleBy; ImpactWildcardEncode; and KSam­

  • More listed components: PreviewImage; SaveImage; Sampler Selector (Image Saver); Scheduler Selector (Comfy) (Image Saver); Seed Generator (Image Saver); String Literal (Image Saver); TY_ExecutionTime; UltimateSDUpscale; UltralyticsDetectorProvider; UnetLoaderGGUF; UpscaleModel­

Configuration

  • Version: v2.0. Base model: Flux.1 D.

Cautions

  • The workflow is described as ComfyUI-only, so verify that ComfyUI is available before use.

    Suggestion · not verified

  • Before running it, verify that the named components and model files are available; the description warns that missing nodes may be reported during loading.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 990626
civitai.com/models/676754

Verified Oct 18

Source excerpts

3 excerpts
NoteOct 18civitai.com/models/676754

Source context: 1847 downloads · Type Workflows · Base model Flux.1 D

NoteAug 4civitai.com/models/676754

Source context: 1787 downloads · Type Workflows · Base model Flux.1 D

NoteJul 18civitai.com/models/676754

Source context: 1747 downloads · Type Workflows · Base model Flux.1 D