FLUX.2

Text-to-image

Black Forest Labs’ FLUX.2 dev is the next-generation text-to-image diffusion transformer, with improved prompt adherence and detail.

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: Lossless for maximum visual fidelity, and Lossy for faster generation with minor perceptual trade-offs. Pick the tab that matches your workload.

Lossless
Lossy

Hardware

H100

Engine

Baseten 1.2

Write the config

Create and move into the project directory:

mkdir flux2-dev && cd flux2-dev

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

config.yaml

model_name: "model:flux2-dev preset:lossless"

base_image:
  image: baseten/qwen-image-2512-h100:v1.2

weights:
  - source: hf://black-forest-labs/FLUX.2-dev@26afe3a78bb242c0a8bb181dcc8937bb16e5c66c
    mount_location: /app/model_cache/FLUX.2-dev
    auth_secret_name: hf_access_token
    ignore_patterns:
      - flux2-dev.safetensors

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

environment_variables:
  SGLANG_WARMUP_SIZE_ON_INIT: "1024x1024"

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

  example_model_input:
    prompt: "A cat holding up a sign that reads 'Hello, world!'"
    size: "1024x1024"
    response_format: "b64_json"
    num_inference_steps: 50
    guidance_scale: 1.0

resources:
  accelerator: H100 # B200 also supported
  use_gpu: true

secrets:
  hf_access_token: null

runtime:
  health_checks:
    # Reduced delays since model weights are now cached
    startup_threshold_seconds: 600   # 10 minutes (was 20)
    restart_threshold_seconds: 300      # 5 minutes
    stop_traffic_threshold_seconds: 300 # 5 minutes

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 "flux2-dev"...
Uploading model...
Uploaded model in 0s
✨ Model flux2-dev was successfully pushed ✨

  Model:       flux2-dev (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": "A cat holding up a sign that reads 'Hello, world!'",
        "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 cat holding up a sign that reads 'Hello, world!'",
    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 cat holding up a sign that reads 'Hello, world!'", "size": "1024x1024", "response_format": "b64_json"}' \
  | jq -r '.data[0].b64_json' | base64 --decode > output.png

FLUX.2 dev with attention caching enabled. Roughly 2× speedup with minor perceptual loss.

Hardware

H100

Engine

Baseten 1.2

Write the config

Create and move into the project directory:

mkdir flux2-dev-lossy && cd flux2-dev-lossy

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

config.yaml

model_name: "model:flux2-dev preset:lossy"

base_image:
  image: baseten/qwen-image-2512-h100:v1.2

weights:
  - source: hf://black-forest-labs/FLUX.2-dev
    mount_location: /app/model_cache/FLUX.2-dev
    auth_secret_name: hf_access_token
    ignore_patterns:
      - flux2-dev.safetensors

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

environment_variables:
  SGLANG_WARMUP_SIZE_ON_INIT: "1024x1024"
  SGLANG_CACHE_DIT_ENABLED: "true"
  SGLANG_CACHE_DIT_WARMUP: "2"
  SGLANG_CACHE_DIT_TAYLORSEER: "true"
  SGLANG_CACHE_DIT_FN: "2"
  SGLANG_CACHE_DIT_BN: "0"

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

  example_model_input:
    prompt: "A cat holding up a sign that reads 'Hello, world!'"
    size: "1024x1024"
    response_format: "b64_json"
    num_inference_steps: 50
    guidance_scale: 1.0

resources:
  accelerator: H100 # B200 also supported
  use_gpu: true

secrets:
  hf_access_token: null

runtime:
  health_checks:
    # Reduced delays since model weights are now cached
    startup_threshold_seconds: 600   # 10 minutes (was 20)
    restart_threshold_seconds: 300      # 5 minutes
    stop_traffic_threshold_seconds: 300 # 5 minutes

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 "flux2-dev-lossy"...
Uploading model...
Uploaded model in 0s
✨ Model flux2-dev-lossy was successfully pushed ✨

  Model:       flux2-dev-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

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 cat holding up a sign that reads 'Hello, world!'",
        "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 cat holding up a sign that reads 'Hello, world!'",
    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 cat holding up a sign that reads 'Hello, world!'", "size": "1024x1024", "response_format": "b64_json"}' \
  | jq -r '.data[0].b64_json' | base64 --decode > output.png

Examples

Models

Engines

Custom Docker servers

Custom Python models

Chains

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

​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

Setup

Write the config

Deploy

Call the model

Write the config

Deploy

Call the model

Next steps