seedinteger
The seed to use for the generation. If not provided, a random seed will be used.
Flux 2 Klein 4B Edit
bfl/flux-2/klein/4b/editFlux 2 Klein 4b by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.
Try the model
Playground
Input
The prompt to edit the image.
Additional Settings More
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
The URLs of the images for editing. A maximum of 4 images are allowed.
48
The number of inference steps to perform. Range: 4 to 8.
The format of the generated image. Allowed values: jpeg, png.
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.
The seed to use for the generation. If not provided, a random seed will be used.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "prompt": "Turn this into a realistic image" }
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
- #63 of 77
- Elo
- 938 ±17
- Gap to #1
- −261
Image-editing arena: people pick the better of two edits of the same image and instruction, without seeing the model names.
- #58Qwen Image Edit Plus 2509965±18
- #59HiDream-O1-Image954±14
- #60Kling Image 3.0 Omni952±14
- #61Vidu Q2951±18
- #62Kling Image O1944±14
- #63FLUX.2 [klein] 4B938±17
- #64GPT Image 1 Mini (medium)934±19
- #65FLUX.1 Kontext [max]932±19
- #66FLUX.1 Kontext [pro]916±19
- #67FIBO Edit915±19
Flux 2 Klein 4B Edit
FLUX.2 [klein] 4B, the smallest FLUX.2 model, built for speed. 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, … |
num_inference_steps | integer 4–8 | 4 | 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
$0.02 per image.
| Request | Price |
|---|---|
| One image | $0.02 |
Failed runs are not charged.
Prompting
- Say which image is the base and what each other image contributes.
- List what must not change.
Limits
- One output image per request.
Also on SandBase
Other FLUX.2 endpoints: bfl/flux-2/max/edit, bfl/flux-2/pro/edit, bfl/flux-2/flex/edit, bfl/flux-2/dev/edit, bfl/flux-2/klein/4b.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "bfl/flux-2/klein/4b/edit",
"images": [
"https://static.sandbase.ai/examples/bfl/flux-2/klein/4b/edit/input_images_0.png"
],
"prompt": "Turn this into a realistic image",
"output_format": "png",
"num_inference_steps": 4
}
SANDBASE_JSON
)
run_id=$(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.
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.
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
imagesarray
The URLs of the images for editing. A maximum of 4 images are allowed.
promptstringrequired
The prompt to edit the image.
aspect_ratiostring
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_formatstring
The format of the generated image.
Default: "png"
Possible values: "jpeg", "png"
num_inference_stepsinteger
The number of inference steps to perform.
Default: 4
Minimum: 4
Maximum: 8
{
"model": "bfl/flux-2/klein/4b/edit",
"images": [
"https://static.sandbase.ai/examples/bfl/flux-2/klein/4b/edit/input_images_0.png"
],
"prompt": "Turn this into a realistic image",
"output_format": "png",
"num_inference_steps": 4
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "BFL/FLUX schema mirror",
"source_url": "https://docs.bfl.ai/flux_2/flux2_overview",
"url": "https://static.sandbase.ai/examples/e942e54d-8b2d-4de3-a6b2-6333e1b9dbd9/output/f993ed09-ff22-45d3-955d-42135857fafb.png"
}
]