WorkflowListedExternal

Basic Krea 2 Workflow

TaskMultiCapabilitiesImage to image · Text to image · UpscalingFamilyKrea 2VersionRelease 3155257 — basicKrea2Workflow_basicKrea2Workflow.jsonEstimated VRAMEstimate unavailableBgrade

Runtime profile

Access: External workflow
Status: Listed
Version: basicKrea2Workflow_basicKrea2Workflow.json
Source: Civitai
Updated: Jul 28, 2026

Source description

By releasing this, I strive to make the best possible starting point for Krea 2 workflows whether you're a beginner or advanced user. Settings are made easy to find, and it includes an optional prompt enhancer using Krea's own text encoder. It also includes the Fantastic Lora Loader which is the best custom node I've ever used to stack loras. I'm including a version with and without Face Fix, a nodepack which I discovered today as I'm writing this. It's super useful but it required me to manually upgrade my huggingface-hub python package to from version 0.24.0 to version 0.34.0 in order to get Comfy to start. Not sure if this is a common issue or not.

Estimated VRAM requirement

Estimate unavailable

Model file sizes are not complete enough to calculate this requirement yet.

AI-generated commentary

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

Purpose

Basic Krea 2 Workflow is for starting Krea 2 image workflows. It accepts prompt text and an optional image input, can enhance prompts and stack LoRAs, and provides image preview and saving paths.

Flow

The 52-node graph combines text generation and encoding, image loading, latent creation, sampling, scaling, preview, and saving.

Inputs and outputs

TextGenerate, CLIPTextEncode, PrimitiveStringMultiline, and LoadImage provide prompt-text and image inputs.
EmptyLatentImage handles latent creation, while PreviewAny and SaveImage provide image preview and saving.

Setup

The listed version is Basic Krea 2 Workflow, published by Pixllvr941, and its base model is Krea 2.

Dependencies

The workflow lists four node packs: comfyui-fantastic-loras, comfyui-kjnodes, comfyui-logic, and rgthree-comfy.
It lists these model files: Krea2_Turbo_convrot_int8mixed.safetensors, krea2_turbo_lora_rank_64_bf16.safetensors, qwen3VLInstruct4bHeretic_int8Convrot.safetensors, and Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors.

Configuration

Settings are described as easy to find, and the optional prompt enhancer uses Krea's own text encoder.
Fantastic Lora Loader stacks LoRAs, and the workflow includes versions with and without Face Fix.

Cautions

Before using it, verify that the listed model files are available: Krea2_Turbo_convrot_int8mixed.safetensors, krea2_turbo_lora_rank_64_bf16.safetensors, qwen3VLInstruct4bHeretic_int8Convrot.safetensors, and Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors.
Suggestion · not verified
The description reports that a manual huggingface-hub upgrade from 0.24.0 to 0.34.0 was needed for Comfy to start; check whether your environment needs the same change.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiSourceVersion 3155257

civitai.com/models/2799044

Verified Jul 28

Source excerpts

1 excerpt

NoteJul 28civitai.com/models/2799044

Source context: 326 downloads · Type Workflows · Base model Krea 2