WorkflowListedExternal

Atomix GGUF txt2img workflow — v2.0

Calling Lora in the prompt instead of node.

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: Aug 8, 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.

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?

Sources

1 source

CivitaiSourceVersion 990626

civitai.com/models/676754

Verified Aug 4

Source excerpts

2 excerpts

NoteAug 4civitai.com/models/676754

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

NoteJul 18civitai.com/models/676754