Flux 2 Dev Text to Image

bfl/flux-2/dev

Flux 2 Dev by BFL - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.

Try the model

Playground

Open playground

Input

Prompt(string)

The prompt to generate an image from.

Additional Settings More

Customize your input with more control.

Guidance Scale(number)

020

Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. Range: 0 to 20.

Number of Inference Steps(integer)

450

The number of inference steps to perform. Range: 4 to 50.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Seed(integer)

The seed to use for the generation. If not provided, a random seed will be used.

Result

Example

What would you like to do next?
Open original

Examples

Select an example to load its inputs and result into the playground.

Input
```
{
  "prompt": "Dutch angle close-up of a survivor in post-apocalyptic setting, dust-covered face, dramatic harsh sunlight creating deep shadows, happy expression, desaturated dystopian color palette, gritty realism"
}
```
Open result ↗

Human preference

Arena

Elo ratings from blind side-by-side votes, compared with other image and video models.

Rankings sourced from Artificial Analysis Arena

Leaderboard: Text to Image
Rank: #46 of 106
Elo: 1000
Gap to #1: −222

Text-to-image arena: people pick the better of two images generated from the same prompt, without seeing the model names.

#41Wan2.6 Text to ImageAlibaba1014±12
#42GPT Image 1 (high)OpenAI1013±12
#43Krea 2 MediumKrea1012±9
#44FLUX.2 [pro]Black Forest LabsOn SandBase1003±10
#45Ideogram 4.0Ideogram1002±10
#46FLUX.2 [dev]Black Forest LabsThis model1000
#47Ming-Image-0.1-DesignInclusionAI999±9
#48P-Image-Ideogram (High)Pruna AI995±14
#49FLUX.2 [dev] TurboFalOn SandBase994±11
#50Cosmos3-Super-Text2Image (agentic)NVIDIA993±10

Flux 2 Dev Text to Image

FLUX.2 [dev], the open-weights 32B FLUX.2 model. Text to image.

Fields

Field	Type	Default	Notes
`prompt`	string, required	—	Text instruction.
`guidance_scale`	number 0–20	2.5	How strictly to follow the prompt.
`num_inference_steps`	integer 4–50	28	More steps add detail and time.
`output_format`	`jpeg` / `png`	`png`	Output file format.
`aspect_ratio`	`21:9` / `16:9` / `3:2` / `4:3` / `5:4` / `1:1` / `4:5` / `3:4` / `2:3` / `9:16`	`16:9`	Output shape.
`seed`	integer	random	Fix it to compare prompt changes.

Billing

$0.012 per image.

Request	Price
One image	$0.012

Failed runs are not charged.

Prompting

Write subject, setting, composition, style, then light.
Quote any text that must appear.

Limits

One output image per request.

Also on SandBase

Other FLUX.2 endpoints: bfl/flux-2/max, bfl/flux-2/pro, bfl/flux-2/flex, bfl/flux-2/turbo, bfl/flux-2/dev/edit.

Start building

Send your first request

Submit this model through the SandBase Unified Run API.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

bfl/flux-2/dev

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "bfl/flux-2/dev",
  "prompt": "Dutch angle close-up of a survivor in post-apocalyptic setting, dust-covered face, dramatic harsh sunlight creating deep shadows, happy expression, desaturated dystopian color palette, gritty realism",
  "aspect_ratio": "16:9",
  "output_format": "png",
  "guidance_scale": 2.5,
  "num_inference_steps": 28
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

2. Authentication

Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.

API key environment variable

export SANDBASE_API_KEY="YOUR_API_KEY"

Keep the key on your server. Do not expose it in browser code or commit it to a repository.

3. Queue

Submit a request

POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.

Fetch request status and result

Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.

Poll run status

curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

4. Files

Hosted files

Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.

Uploading images

Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.

5. Schema

Input

`seed`integer

The seed to use for the generation. If not provided, a random seed will be used.

`prompt`stringrequired

The prompt to generate an image from.

`aspect_ratio`string

The aspect ratio of the generated image.

Default: "16:9"

Possible values: "21:9", "16:9", "3:2", "4:3", "5:4", "1:1", "4:5", "3:4", "2:3", "9:16"

`output_format`string

The format of the generated image.

Default: "png"

Possible values: "jpeg", "png"

`guidance_scale`number

Guidance Scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

Default: 2.5

Minimum: 0

Maximum: 20

`num_inference_steps`integer

The number of inference steps to perform.

Default: 28

Minimum: 4

Maximum: 50

Request body

{
  "model": "bfl/flux-2/dev",
  "prompt": "Dutch angle close-up of a survivor in post-apocalyptic setting, dust-covered face, dramatic harsh sunlight creating deep shadows, happy expression, desaturated dystopian color palette, gritty realism",
  "aspect_ratio": "16:9",
  "output_format": "png",
  "guidance_scale": 2.5,
  "num_inference_steps": 28
}

Output

A completed run exposes its result in output. The following is the model’s saved example, not a new generation.

Example output JSON

[
  {
    "source": "BFL/FLUX schema mirror",
    "source_url": "https://docs.bfl.ai/flux_2/flux2_overview",
    "url": "https://static.sandbase.ai/examples/9c5d6e59-b957-46c7-8c6f-2295af639f91/output/be5ccf4b-2861-4247-b4d9-3351cb2e3cf7.png"
  }
]

Flux 2 Dev Text to Image

Playground

Examples

Arena

Flux 2 Dev Text to Image

Fields

Billing

Prompting

Limits

Also on SandBase

Send your first request

2. Authentication

3. Queue

Submit a request

Fetch request status and result

4. Files

Hosted files

Uploading images

5. Schema

Input

seedinteger

promptstringrequired

aspect_ratiostring

output_formatstring

guidance_scalenumber

num_inference_stepsinteger

Output

Flux 1 Schnell ↗

Flux 2 Flash Text to Image ↗

Flux 2 Flex Text to Image ↗

Flux 2 Klein 4B Text to Image ↗

Flux 2 Klein 9B Text to Image ↗

Flux 2 Max Text to Image ↗

`seed`integer

`prompt`stringrequired

`aspect_ratio`string

`output_format`string

`guidance_scale`number

`num_inference_steps`integer