Skip to content
WorkflowListedExternal
Open source

Flux.2 Klein Image Edit Workflow — V2.0

(This is not an exhaustive changelog)

Sourcecivitai.com/models/2318837
TaskMultiCapabilitiesImage edit · UpscalingFamilyFLUXVersionRelease 2628725 — flux2_klein_editV2.jsonEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
flux2_klein_editV2.json
Source
Civitai
Updated
Oct 18, 2026

Source description

Upload of 2.0

(This is not an exhaustive changelog)

Updated to V2.0 :

added upscaler

What you need

Model files
3.9 GiB known subtotal

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

Requirements

Models

5

Node packs

2

  • comfyui-gguf

    Possible

    Node pack · Registry

  • rgthree-comfy

    Found

    Node pack · Registry

AI-generated commentary

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

Purpose

  • Flux.2 Klein Image Edit Workflow — V2.0 is a ComfyUI workflow for editing a loaded image with Flux.2 Klein 4B; it takes an image, text, a reference latent, a seed, and random noise, and can output an edited image that can be upscaled, compared, and saved.

Flow

  • The workflow encodes and decodes images with a VAE, then samples with text conditioning, a reference latent, a seed, and random noise.

  • Version V2.0 adds an upscaling path and includes image comparison and image saving.

Inputs and outputs

  • Use LoadImage, CLIPTextEncode, ReferenceLatent, Seed (rgthree), and RandomNoise for the image, text, reference-latent, seed, and noise inputs.

  • VAEDecode produces the decoded image; ImageUpscaleWithModel, Image Comparer (rgthree), and SaveImage provide upscaling, comparison, and saving stages.

Setup

  • The listed custom nodes are ComfyUI-Manager, rgthree-comfy, and ComfyUI-GGUF.

  • Place the diffusion model under .../ComfyUI/models/diffusion_models/, the text encoder under .../ComfyUI/models/text_encoders/, and the VAE under .../ComfyUI/models/vae/.

    Suggestion · not verified

Dependencies

  • The workflow lists these required model files: 4x_foolhardy_Remacri.pth (upscaler), flux-2-klein-4b-BF16.gguf and flux-2-klein-4b-fp8.safetensors (UNet), flux2-vae.safetensors (VAE), and qwen_3_4b.safetensors (text encoder).

  • The named node packs are rgthree-comfy and comfyui-gguf.

Configuration

  • For the distilled setup, use 4 steps, CFG 1.0, and the Euler sampler.

    Suggestion · not verified

  • The listed model choices include flux2-klein-4b or other diffusion-model versions, qwen_3__4b or qwen_3__8b, and flux2-vae.

Cautions

  • Before setup, compare the listed choices—flux2-klein-4b, qwen_3__4b, and flux2-vae—with the exact files you install: flux-2-klein-4b-BF16.gguf or flux-2-klein-4b-fp8.safetensors, qwen_3_4b.safetensors, and flux2-vae.safetensors.

    Suggestion · not verified

  • Before setup, verify which package provides comfyui-gguf and whether qwen_3_4b.safetensors is the file you intend to use for the qwen_3__4b text-encoder choice.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 2628725
civitai.com/models/2318837

Verified Oct 18

Source excerpts

3 excerpts
NoteOct 18civitai.com/models/2318837

Source context: 4153 downloads · Type Workflows · Base model Flux.2 Klein 4B

NoteAug 7civitai.com/models/2318837

Source context: 3499 downloads · Type Workflows · Base model Flux.2 Klein 4B

NoteJul 18civitai.com/models/2318837

Source context: 3295 downloads · Type Workflows · Base model Flux.2 Klein 4B