Flux 2 Dev Edit

bfl/flux-2/dev/edit

Flux 2 Dev Edit is BFL's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

Try the model

Playground

Open playground

Input

Prompt(string)

The prompt to edit the image.

Additional Settings More

Customize your input with more control.

Image URLs(array)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

The URLs of the images for editing. A maximum of 4 images are allowed, if more are provided, only the first 4 will be used.

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": "Change his clothes to casual suit and tie"
}
```
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: Image Editing
Rank: #48 of 77
Elo: 1000
Gap to #1: −199

Image-editing arena: people pick the better of two edits of the same image and instruction, without seeing the model names.

#43FLUX.2 [dev] TurboFalOn SandBase1019±18
#44FLUX.2 [klein] 9BBlack Forest LabsOn SandBase1015±13
#45FLUX.2 [dev] FlashFalOn SandBase1012±18
#46FLUX.2 [pro]Black Forest LabsOn SandBase1012±15
#47Step Image Edit 2StepFun1009±13
#48FLUX.2 [dev]Black Forest LabsThis model1000
#49FLUX.2 [max]Black Forest LabsOn SandBase999±13
#50FLUX.2 [flex]Black Forest LabsOn SandBase999±17
#51GPT Image 1 (high)OpenAI995±18
#52Qwen Image Edit Plus 2511AlibabaOn SandBase991±18

Flux 2 Dev Edit

FLUX.2 [dev], the open-weights 32B FLUX.2 model. Edit or combine images with an instruction.

Fields

Field	Type	Default	Notes
`prompt`	string, required	—	Text instruction.
`images`	image URL[]	—	Images to edit or combine, Image 1, Image 2, …
`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`	—	Output shape.
`seed`	integer	random	Fix it to compare prompt changes.

Billing

$0.024 per image.

Request	Price
One image	$0.024

Failed runs are not charged.

Prompting

Say which image is the base and what each other image contributes.
List what must not change.

Limits

One output image per request.

Also on SandBase

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

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/edit

# 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 $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "bfl/flux-2/dev/edit",
  "images": [
    "https://static.sandbase.ai/examples/bfl/flux-2/dev/edit/input_images_0.png"
  ],
  "prompt": "Change his clothes to casual suit and tie",
  "output_format": "png",
  "guidance_scale": 2.5,
  "num_inference_steps": 28
}
SANDBASE_JSON
)
run_id=$(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.

`images`array

The URLs of the images for editing. A maximum of 4 images are allowed, if more are provided, only the first 4 will be used.

`prompt`stringrequired

The prompt to edit the image.

`aspect_ratio`string

The aspect ratio of the generated image.

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/edit",
  "images": [
    "https://static.sandbase.ai/examples/bfl/flux-2/dev/edit/input_images_0.png"
  ],
  "prompt": "Change his clothes to casual suit and tie",
  "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/60115522-32c0-4fd3-8a11-70985a71fc46/output/13b888bf-dd2c-40cd-acc9-f5c4ca7a6209.png"
  }
]

Flux 2 Dev Edit

Playground

Examples

Arena

Flux 2 Dev Edit

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

imagesarray

promptstringrequired

aspect_ratiostring

output_formatstring

guidance_scalenumber

num_inference_stepsinteger

Output

Flux 2 Flash Edit ↗

Flux 2 Flex Edit ↗

Flux 2 Klein 4B Edit ↗

Flux 2 Klein 9B Edit ↗

FLUX.1 Kontext [dev] ↗

Flux 2 Max Edit ↗

`seed`integer

`images`array

`prompt`stringrequired

`aspect_ratio`string

`output_format`string

`guidance_scale`number

`num_inference_steps`integer