Krea 2: Generate consistent images with unified .char model

Once your .char file is generated for your character, You are ready to use it for Krea2 generation.

• To train a unified .char model for Flux2 & Krea2 both: Flux 2 + Krea 2: Multi model portable consistent characters

Requirements

• Nvidia GPU: 16GB+ VRAM
• Inline Studio installed

Steps

This is a step by step guide to run this workflow.

Step 1: Setup Inline Studio

• Visit installation instruction on our Github readme to setup Inline Studio on local machine with your own GPU.
• No GPU? Launch Inline Studio via official template on Runpod

Step 2: Download workflow

You can download this workflow from the download icon next to title. Click on it & the json file will be saved to your local machine.

Step 3: Drop the workflow

• Open Inline Studio canvas, create a new project or use an existing project
• Drag & drop the saved workflow into the canvas

Step 4: Install models

As soon as you dropped the workflow, missing model popup will guide you through model download.

Models required:

core/models/
  diffusion_models/  krea2_turbo_bf16.safetensors
  text_encoders/     qwen3vl_4b_bf16.safetensors
  vae/               qwen_image_vae_diffusers.safetensors
  characters/        emmy-s500-v2.char <--- sample uploaded on HF

Note: emmy-s500-v2.char is not in the registry as it's a test sample, to access this in Inline Studio, download the model from Huggingface & place it under core/models/characters/

Step 5: Load inputs

This workflow requires only prompt, which is already embedded in workflow json. .char model is loaded with Load Character node

Step 6: Run Workflow

Click over Flux node & hit Run Graph.

That's it.

What's next?

As of now .char is only supported with Flux2 family & Krea2 nodes. For any issue or support, reach me out on Discord.