Flux 2 + Krea 2: Multi model portable consistent characters(Training only)

This workflow demonstrates, build a character that is supported across multi model generation pipeline. For this workflow we are combining Flux & Krea2, so that same .char exported file works across both flux family & Krea 2 generation nodes.

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_raw_bf16.safetensors 
  text_encoders/     qwen3vl_4b_bf16.safetensors   
  vae/               qwen_image_vae_diffusers.safetensors 
  annotators/        face_detection_yunet_2023mar.onnx
  annotators/        face_recognition_sface_2021dec.onnx
  annotators/        dinov2-base/                               <-- folder

Step 5: Load inputs

Download both inputs in this given workflow & drop them in Load Assets node or you can add your own face images.

Step 6: Run Workflow

Flux generation node is already attached with character workflow in order to immediately text the generation. Once you will run the workflow, on successful run it will save a .char file under /core/model/characters folder.

Step 7: Monitor Train

Default steps are 800, it will take somewhere around an hour to finish training, once training is completed, it should export lora file & as well as a .char file. Locate both files under models side panel.

Once exported, both files will be available in Load Lora & Load Character nodes.

Step 6: Reuse .char without rebuilding(Optional)

Most of the workflow part is responsible for building char model but you might not need to build model on each run.

If you just want to generate using same generated .char, Setup a new separate generation graph:

Load Character Node -> Flux Generation Node

As of now .char is only supported with Flux node. For any issue or support, reach me out on Discord.