Krea 2 Turbo

Text-to-image

Krea 2 Turbo is Krea’s 12B flow-matching image generation model: a single-stream MMDiT backbone paired with a Qwen3-VL text encoder and the Qwen-Image VAE. The Turbo variant is distilled to 8 denoising steps with classifier-free guidance (CFG) disabled, generating a 1024px image in roughly 1.5 to 2 seconds and a 2048px image in 6 to 8 seconds on an H100, with native output resolutions from 1024 to 2048. For example prompts and prompting techniques, see the Krea 2 prompting guide. The weights ship under the Krea 2 Community License, which requires an Enterprise License from Krea for commercial use by companies over $1M in annual revenue.

Setup

Install the Baseten CLI and sign in, then install the client library for the tab you’ll use: requests for the Python tab, or the OpenAI SDK for the OpenAI tab.

Install and sign in to Baseten

macOS or Linux
Windows

Terminal

brew tap basetenlabs/baseten
brew trust --formula basetenlabs/baseten/baseten
brew install baseten

Download and extract the Windows archive for the latest Baseten CLI release:

Terminal

$release = Invoke-RestMethod https://api.github.com/repos/basetenlabs/baseten-cli/releases/latest
$asset = $release.assets | Where-Object { $_.name -like "*_windows_amd64.zip" }
Invoke-WebRequest $asset.browser_download_url -OutFile baseten.zip
Expand-Archive -Force baseten.zip .

Move baseten.exe to a directory on your PATH.

For other platforms or a specific version, see the Baseten CLI install reference.

baseten auth login

Install requests

uv pip install requests

Install the OpenAI SDK

uv pip install openai

To install without Homebrew, see the Baseten CLI install reference. This variant ships in 2 presets tuned for different goals: Lossy for faster generation with minor perceptual trade-offs, and Perf-Optimized. Pick the tab that matches your workload.

Lossy
Perf-Optimized

This preset serves Krea 2 Turbo on a single H100, with the full bfloat16 weights loaded in GPU memory and the SGLang diffusion stack’s 8-step distilled sampling for fast image generation.

Hardware

H100

Engine

SGLang 1.3

Write the config

Create and move into the project directory:

mkdir krea-2-turbo-lossy && cd krea-2-turbo-lossy

Then create a file named config.yaml and paste the following:

config.yaml

model_name: "model:krea-2-turbo preset:lossy"

base_image:
  image: baseten/sglang-diffusion-h100:v1.3

weights:
  - source: hf://krea/Krea-2-Turbo@98e0fe118d17c9e3547fbb2e25acdbae2cadf7c7
    mount_location: /app/model_cache/krea-2-turbo
    auth_secret_name: hf_access_token
    ignore_patterns: ["**/turbo.safetensors"]

docker_server:
  start_command: /app/start_sglang.sh
  readiness_endpoint: /health_generate
  liveness_endpoint: /health_generate
  predict_endpoint: /v1/images/generations
  server_port: 8000

model_metadata:
  repo_id: krea/Krea-2-Turbo
  output_media:
    - json_path: "data[*].b64_json"
      media_type: "image/png"
      encoding: "base64"
      label: "Generated Image"

  visual_gen:
    extra_sglang_args:
      enable_fp8: "1"
      enable_fp4_dit: "0"
      enable_cache_dit: "1"
      dit_cpu_offload: "false"
      text_encoder_cpu_offload: "false"
      image_encoder_cpu_offload: "false"
      vae_cpu_offload: "false"
      trust_remote_code: "false"
      b10_cpu_memory_saving: "0"
      num_gpus: "1"
      warmup_resolutions: "1024x1024 2048x2048"
      lora_path: ""

  example_model_input:
    prompt: "immense rocket launch exhaust as seen from extremely close up"
    n: 1
    size: "1024x1024"
    response_format: "b64_json"

resources:
  accelerator: H100
  use_gpu: true

secrets:
  - hf_access_token

runtime:
  health_checks:
    startup_threshold_seconds: 1200
    restart_threshold_seconds: 300
    stop_traffic_threshold_seconds: 300

This deployment loads the 34 GB bfloat16 checkpoint of krea/Krea-2-Turbo on a single H100 and serves it with the SGLang diffusion stack. The server exposes an OpenAI-compatible images API at /v1/images/generations that returns base64-encoded images.

Deploy

Push the config to Baseten with the Baseten CLI, or with the Truss CLI if you prefer it:

baseten model push

uvx truss push

You should see output similar to:

Pushing model "krea-2-turbo-lossy"...
Uploading model...
Uploaded model in 0s
✨ Model krea-2-turbo-lossy was successfully pushed ✨

  Model:       krea-2-turbo-lossy (abc1d2ef)
  Deployment:  xyz123
  Environment: production

🪵 View logs:
   deployment:   baseten model deployment logs --model-id abc1d2ef --deployment-id xyz123
   environment:  baseten model environment logs --model-id abc1d2ef --environment production  (once deployed)
   app:          https://app.baseten.co/models/abc1d2ef/logs/xyz123

🚀 Invoke your model:
   URL:  https://model-abc1d2ef.api.baseten.co/deployment/xyz123/predict
   CLI:  baseten model predict --model-id abc1d2ef

baseten model push prints your model ID (abc1d2ef in the example). The examples below use it wherever you see {model_id}, and read your API key from the BASETEN_API_KEY environment variable.

Call the model

Use the /v1/images/generations endpoint to generate your model’s images.The deployment returns the generated image as base64-encoded bytes. Decode the response to write the image to disk. The size parameter sets the output resolution in pixels.

Python
OpenAI
cURL

main.py

import base64
import os
import requests

response = requests.post(
    "https://model-{model_id}.api.baseten.co/environments/production/sync/v1/images/generations",
    headers={"Authorization": f"Bearer {os.environ['BASETEN_API_KEY']}"},
    json={
        "prompt": "immense rocket launch exhaust as seen from extremely close up",
        "size": "1024x1024",
        "response_format": "b64_json",
    },
)

image_b64 = response.json()["data"][0]["b64_json"]
with open("output.png", "wb") as f:
    f.write(base64.b64decode(image_b64))

main.py

import base64
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BASETEN_API_KEY"],
    base_url="https://model-{model_id}.api.baseten.co/environments/production/sync/v1",
)

image = client.images.generate(
    prompt="immense rocket launch exhaust as seen from extremely close up",
    size="1024x1024",
    response_format="b64_json",
)

with open("output.png", "wb") as f:
    f.write(base64.b64decode(image.data[0].b64_json))

curl -s https://model-{model_id}.api.baseten.co/environments/production/sync/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -d '{"prompt": "immense rocket launch exhaust as seen from extremely close up", "size": "1024x1024", "response_format": "b64_json"}' \
  | jq -r '.data[0].b64_json' | base64 --decode > output.png

Close-up of a rocket lifting off at night, dense engine exhaust plumes and billowing smoke lit from within by the flames — Generated by this deployment from the rocket prompt above at 2048x2048, in 8.5 seconds on an H100

Hardware

H100

Engine

SGLang (1.4-fp8krea-exp build)

Write the config

Create and move into the project directory:

mkdir krea-2-turbo && cd krea-2-turbo

Then create a file named config.yaml and paste the following:

config.yaml

model_name: "model:krea-2-turbo preset:perf-optimized"
# NOTE for docs/productization: as measured this config used experimental image
# v1.4-fp8krea-exp (built from unmerged fork branch fde/krea2-fp8). The shipping
# equivalent is the next official tag (expected v1.4) built from b10-main after
# fork PR #64 merges; swap the base_image below accordingly.

base_image:
  image: baseten/sglang-diffusion-h100:v1.4-fp8krea-exp

weights:
  - source: hf://krea/Krea-2-Turbo@98e0fe118d17c9e3547fbb2e25acdbae2cadf7c7
    mount_location: /app/model_cache/krea-2-turbo
    auth_secret_name: hf_access_token

docker_server:
  start_command: /app/start_sglang.sh
  readiness_endpoint: /health_generate
  liveness_endpoint: /health_generate
  predict_endpoint: /v1/images/generations
  server_port: 8000

model_metadata:
  repo_id: krea/Krea-2-Turbo
  output_media:
    - json_path: "data[*].b64_json"
      media_type: "image/png"
      encoding: "base64"
      label: "Generated Image"

  visual_gen:
    extra_sglang_args:
      enable_fp8: "1"
      enable_fp4_dit: "0"
      enable_cache_dit: "1"
      dit_cpu_offload: "false"
      text_encoder_cpu_offload: "false"
      image_encoder_cpu_offload: "false"
      vae_cpu_offload: "false"
      trust_remote_code: "false"
      b10_cpu_memory_saving: "0"
      num_gpus: "1"
      warmup_resolutions: "1024x1024 2048x2048"
      lora_path: ""

  example_model_input:
    prompt: "A lighthouse on a rocky coast at golden hour, waves breaking below, warm light across the water"
    n: 1
    size: "1024x1024"
    response_format: "b64_json"

resources:
  accelerator: H100
  use_gpu: true

secrets:
  - hf_access_token

runtime:
  health_checks:
    startup_threshold_seconds: 1200
    restart_threshold_seconds: 300
    stop_traffic_threshold_seconds: 300

Deploy

Push the config to Baseten with the Baseten CLI, or with the Truss CLI if you prefer it:

baseten model push

uvx truss push

You should see output similar to:

Pushing model "krea-2-turbo"...
Uploading model...
Uploaded model in 0s
✨ Model krea-2-turbo was successfully pushed ✨

  Model:       krea-2-turbo (abc1d2ef)
  Deployment:  xyz123
  Environment: production

🪵 View logs:
   deployment:   baseten model deployment logs --model-id abc1d2ef --deployment-id xyz123
   environment:  baseten model environment logs --model-id abc1d2ef --environment production  (once deployed)
   app:          https://app.baseten.co/models/abc1d2ef/logs/xyz123

🚀 Invoke your model:
   URL:  https://model-abc1d2ef.api.baseten.co/deployment/xyz123/predict
   CLI:  baseten model predict --model-id abc1d2ef

Call the model

Python
OpenAI
cURL

main.py

import base64
import os
import requests

response = requests.post(
    "https://model-{model_id}.api.baseten.co/environments/production/sync/v1/images/generations",
    headers={"Authorization": f"Bearer {os.environ['BASETEN_API_KEY']}"},
    json={
        "prompt": "A lighthouse on a rocky coast at golden hour, waves breaking below, warm light across the water",
        "size": "1024x1024",
        "response_format": "b64_json",
    },
)

image_b64 = response.json()["data"][0]["b64_json"]
with open("output.png", "wb") as f:
    f.write(base64.b64decode(image_b64))

main.py

import base64
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BASETEN_API_KEY"],
    base_url="https://model-{model_id}.api.baseten.co/environments/production/sync/v1",
)

image = client.images.generate(
    prompt="A lighthouse on a rocky coast at golden hour, waves breaking below, warm light across the water",
    size="1024x1024",
    response_format="b64_json",
)

with open("output.png", "wb") as f:
    f.write(base64.b64decode(image.data[0].b64_json))

curl -s https://model-{model_id}.api.baseten.co/environments/production/sync/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $BASETEN_API_KEY" \
  -d '{"prompt": "A lighthouse on a rocky coast at golden hour, waves breaking below, warm light across the water", "size": "1024x1024", "response_format": "b64_json"}' \
  | jq -r '.data[0].b64_json' | base64 --decode > output.png

Next steps

Call your model

Endpoint anatomy, authentication, and sync versus async inference

Autoscaling

Scale replicas with traffic, including scale to zero

Krea 2 prompting guide

Example prompts and prompting techniques from the Krea team

Examples

Models

Engines

Custom Docker servers

Custom Python models

Chains

Post-training

Baseten for Model Labs

Setup

Hardware

Engine

Write the config

Deploy

Call the model

Hardware

Engine

Write the config

Deploy

Call the model

Next steps

Call your model

Autoscaling

Krea 2 prompting guide

​Setup

Hardware

Engine

​Write the config

​Deploy

​Call the model

Hardware

Engine

​Write the config

​Deploy

​Call the model

​Next steps

Call your model

Autoscaling

Krea 2 prompting guide

Setup

Write the config

Deploy

Call the model

Write the config

Deploy

Call the model

Next steps