WorkflowListedExternal

Flux.2 Workflow with optional Multi-image reference — v1.0

Initialize: Load model, CLIP, VAE and optional LoRA. Make your prompt (divided into 2 parts if you prefer to make separate prompt for edit instructions and overall).

Sourcecivitai.com/models/2197238

TaskMultiCapabilitiesImage to image · UpscalingFamilyFLUXVersionRelease 2474002 — Yorgash Flux.2 flow.jsonEstimated VRAMNot yet characterizedUnratedgrade

Runtime profile

Access: External workflow
Status: Listed
Version: Yorgash Flux.2 flow.json
Source: Civitai
Updated: Nov 3, 2026

Source description

No release description captured.

What you need

Model files: 46.8 GiB known subtotal

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

Requirements

Models

aidmaMJ61Flux.2v0.5.safetensors
Not resolved
LoRA · Unknown
flux2-dev-fp8_scaled.safetensors
Found
Diffusion model · 30.0 GB · SAFETENSORS · Unknown
flux2-vae.safetensors
Repository matched
VAE · Unknown
mistral_3_small_flux2_fp8.safetensors
Found
Text encoder · 16.8 GB · SAFETENSORS · FP8 (unverified) · Unknown
RealESRGAN_x4plus_anime_6B.pth
Found
Upscaler · 17.1 MB · PTH · Unknown

Node packs

comfyui-crystools
Found
Node pack · Registry
comfyui-easy-use
Found
Node pack · Registry
Found
Node pack · Registry
comfyui-utils-nodes
Found
Node pack · Registry

AI-generated commentary

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

Purpose

Use this Flux.2 workflow with a prompt, optional reference images, and optional LoRA; it loads the model, CLIP, and VAE and offers initial, upscaled, or blended image outputs.

Flow

Load the model, CLIP, VAE, and optional LoRA, then enter a prompt that can be split into edit instructions and overall text.
Choose whether to use reference images, then use common sampler options with optional upscaling or blending.

Inputs and outputs

Provide a prompt, optionally divided into separate edit-instruction and overall text.
Four reference images are included, and more can be added by copying a reference-image node.
Outputs can include the initial image, an upscaled image, or a blend of both; normal-and-upscaled batch handling saves the initial and upscaled images.

Setup

The workflow uses Flux.2 D and is published by Yorgash.

Dependencies

Node packs listed for this workflow are ComfyUI-Easy-Use, ComfyUI-Crystools, ComfyUI-KJNodes, and ComfyUI-utils-nodes.
Model files listed are flux2-dev-fp8_scaled.safetensors, flux2-vae.safetensors, mistral_3_small_flux2_fp8.safetensors, aidmaMJ61Flux.2v0.5.safetensors, and RealESRGAN_x4plus_anime_6B.pth.

Configuration

Turn reference images on or off, split the prompt into edit instructions and overall text, and choose normal, upscaled, or blended output handling.
The listed node-pack versions are ComfyUI-Crystools 1.27.3, ComfyUI-Easy-Use 1.3.3, ComfyUI-KJNodes 1.1.7, and ComfyUI-utils-nodes 1.3.7.

Cautions

Verify the exact files for flux2-dev-fp8_scaled.safetensors, flux2-vae.safetensors, and aidmaMJ61Flux.2v0.5.safetensors before setup because no checksums are listed for them.
Suggestion · not verified
No license is specified for the listing.

Does this need to be edited?

Sources

1 source

CivitaiPrimaryVersion 2474002

civitai.com/models/2197238

Verified Nov 3