Krea-2 ComfyUI Workflow Example

Krea 2 is a text-to-image model designed for high aesthetic quality and stylistic diversity. It comes in two variants: RAW (base) and Turbo (distilled).

Krea 2 is an image generation model from Krea AI, trained from scratch and focused on creative and stylistic exploration.

Krea 2 ships as two models designed to work together: train LoRAs on RAW, run inference on Turbo:

• Krea 2 RAW: the base model with full-step sampling (52 steps). No distillation, diverse and highly malleable, ideal for fine-tuning and LoRA training.
• Krea 2 Turbo: an 8-step distilled checkpoint for fast, high-quality generation. LoRAs trained on RAW apply seamlessly to Turbo.

License: Krea AI Community License

Watch the Launch Event

To learn more about Krea 2, the story behind its development, its capabilities, and what it means for the open-source ecosystem, watch the launch event recording above (featuring Victor Perez, Miguel Lara, and ComfyAnonymous).

Available Model Weights

Krea 2 is available in two variants:

• Krea 2 RAW: the base model with full-step sampling (52 steps). Designed for diversity and malleability, best for fine-tuning and LoRA training.
• Krea 2 Turbo: an 8-step distilled checkpoint built for fast, high-quality generation. LoRAs trained on RAW apply seamlessly to Turbo.

Related Links:

• Krea 2 on Hugging Face (RAW)
• Krea 2 on Hugging Face (Turbo)
• Comfy-Org/Krea-2 (ComfyUI models)
• Official GitHub repository
• Technical report

Krea-2 Turbo text-to-image workflow

Run in Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Krea-2” in Template Library

Local users

Make sure your ComfyUI is updated.

• Download ComfyUI
• Update Guide

Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.

If nodes are missing when loading a workflow, possible reasons:

1. You are not using the latest ComfyUI version (Nightly version)
2. Some nodes failed to import at startup

Cloud users

• Cloud will update after ComfyUI stable release.

So, if you find any core node missing in this document, it might be because the new core nodes have not yet been released in the latest stable version. Please wait for the next stable release.

The workflow is organized into a few parts:

1. Text to Image (Krea-2 Turbo) subgraph: the core generation pipeline, containing model loading, prompt handling, sampling, and VAE decode
2. ResolutionSelector: choose your desired output resolution. Krea 2 supports outputs from 1K to 2K — set the megapixels value to 2.0 to get 2K resolution.
3. CustomCombo (LoRA selector): a pre-built trigger word selector for the available style LoRAs. If you download additional LoRAs, you can customize this selector and pair them with the corresponding LoRA files accordingly.
4. SaveImage: saves the generated image

Learn about Subgraph

This workflow uses Subgraph nodes for modular processing. Check out the Subgraph documentation to learn how to customize and extend the workflow.

Single-click generation

At its simplest, just enter a text prompt in the subgraph, select a resolution, and click Queue Prompt. The defaults (8 steps, prompt enhancement enabled, no LoRA) produce a high-quality image with minimal configuration.

Workflow controls

The Text to Image (Krea-2 Turbo) subgraph exposes the following controls:

Control	Description
Text String (User Prompt)	The text prompt describing the image you want to generate
prompt_enhance	Toggle LLM-powered prompt expansion on/off
LLM_max_token	Maximum token length for prompt enhancement
Width / Height	Output resolution (controlled by ResolutionSelector)
Seed	Random seed for reproducibility
enable_lora?	Enable or disable style LoRA
LoRA Strength	Strength of the applied style LoRA
LoRA Trigger Word	Auto-populated trigger word for the selected LoRA

Style LoRAs

Krea also released a collection of style LoRAs for Krea 2. Select one in the CustomCombo node and enable enable_lora? in the subgraph to apply the style:

LoRA	Trigger Word	Recommended Strength	Download
krea2_darkbrush	monochrome ink wash style	1.0	Download
krea2_dotmatrix	monochrome stippling style	1.0	Download
krea2_kidsdrawing	naive expressive sketch style	1.0	Download
krea2_neondrip	textured abstract style	1.0	Download
krea2_rainywindow	rainy window style	1.0	Download
krea2_retroanime	purple retro anime style	1.0	Download
krea2_softwatercolor	art deco watercolor style	1.0	Download
krea2_sunsetblur	ethereal motion blur style	1.0	Download
krea2_vintagetarot	vintage tarot style	1.0	Download

Place the .safetensors files in ComfyUI/models/loras/.

Model downloads

For local use, download the ComfyUI-optimized model files from Comfy-Org/Krea-2.

Diffusion Model (FP8)

krea2_turbo_fp8_scaled.safetensors: Turbo FP8 (recommended for most users)

Text Encoder (FP8)

qwen3vl_4b_fp8_scaled.safetensors: Qwen3VL-4B text encoder

VAE

qwen_image_vae.safetensors

Style LoRAs

View all style LoRAs on Hugging Face

Other model variants (BF16, NVFP4, MXFP8) are also available for users with higher-end hardware.

Model storage location

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   └── krea2_turbo_fp8_scaled.safetensors
│   ├── 📂 text_encoders/
│   │   └── qwen3vl_4b_fp8_scaled.safetensors
│   ├── 📂 vae/
│   │   └── qwen_image_vae.safetensors
│   └── 📂 loras/
│       └── krea2_softwatercolor.safetensors (and other style LoRAs)

Krea-2 Turbo style reference workflow

Run in Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Krea-2 Style Reference” in Template Library

The style reference workflow builds on the Krea-2 Turbo pipeline by adding reference image conditioning. Upload one or more reference images to influence the aesthetic style, mood, and visual direction of the generated output.

The workflow is organized into a few parts:

1. Image Style Reference (Krea-2 Turbo) subgraph: the core generation pipeline with style reference support, containing model loading, reference image conditioning, prompt handling, and sampling
2. LoadImage: upload your style reference images
3. ResolutionSelector: choose your desired output resolution. Krea 2 supports outputs from 1K to 2K.
4. SaveImage: saves the generated image

Using style reference

1. Upload reference images — use the LoadImage node to load one or more style reference images
2. Enter your prompt — type a text description in the subgraph’s user prompt input
3. Select a model variant — choose the model checkpoint in the subgraph’s model selector
4. Adjust settings — configure resolution, seed, and optionally enable prompt enhancement
5. Click Queue — press Ctrl+Enter to generate

This style reference workflow uses a dedicated diffusion model and LoRA. The text encoder and VAE are shared with the text-to-image workflow.

Diffusion Model (INT8)

krea2_turbo_int8_convrot.safetensors

Text Encoder (FP8)

qwen3vl_4b_fp8_scaled.safetensors: Qwen3VL-4B text encoder

VAE

qwen_image_vae.safetensors

Style Reference LoRA

krea2_style_reference.safetensors

Place the files in the following directories:

📂 ComfyUI/
├── 📂 models/
│   ├── 📂 diffusion_models/
│   │   └── krea2_turbo_int8_convrot.safetensors
│   ├── 📂 text_encoders/
│   │   └── qwen3vl_4b_fp8_scaled.safetensors
│   ├── 📂 vae/
│   │   └── qwen_image_vae.safetensors
│   └── 📂 loras/
│       └── krea2_style_reference.safetensors