FLUX 3 Klein Edit API

blackforestlabs/flux-3-klein/edit

image_urls 1–10 · 1K · 2K · 4K

FLUX 3 Klein Edit turns one to ten input images and a written instruction into edited or combined results at 1K, 2K or 4K, priced the same as generation. It keeps the subjects you name from each image while changing backgrounds, outfits, materials or style.

Get API Key

Input

PromptRequired

Image UrlsRequired

Drag and drop files, paste from clipboard, or provide a URL. 1–10 public HTTP(S) image URLs, in prompt order.

1/10 files added

SizeOptional

ResolutionOptional

NOptional

Output FormatOptional

Enable Safety CheckerOptional

OutputReady

Estimated cost: 1.8 credits · $0.0090

Credits are reserved when the task is submitted and refunded in full if it fails.

Continue using

FLUX 3 Klein Text to Image Ideogram 4.5 Edit Nano Banana 2.1 Edit

Examples

Dress the person from the first image in the jacket from the second image, standing on the street from the third image. Keep the face, hairstyle and pose from the first image.

Restyle the living room in the first image with mid-century furniture and warm evening lamp light. Keep the windows, walls and floor layout unchanged.

REST API

Quick Start

This flow submits one valid FLUX 3 Klein Edit request, captures its task_id, and reads result file URLs after the asynchronous task ends.

Connect to the Vidgo API

Create an API key, keep it on the server, and send it as Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one task

Send the current model ID and an input object to the unified submit endpoint. input may only contain the fields listed for this endpoint; any other field returns 400.

Submit request

curl --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "blackforestlabs/flux-3-klein/edit",
  "input": {
    "prompt": "Keep the sneaker from the first image exactly as it is and place it on a snowy wooden porch step with soft winter daylight.",
    "size": "1:1",
    "resolution": "1K",
    "n": 1,
    "output_format": "png",
    "enable_safety_checker": true,
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-3-klein/edit/v1/01/input-01-product-placeholder.png"
    ]
  }
}'

Wait for the result

Read data.task_id and poll only while status is not_started or running. Stop on both finished and failed.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll every 2–5 seconds and back off on 429/5xx. Or provide top-level callback_url to receive a terminal-state callback.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "task-example",
    "status": "not_started",
    "created_time": "2026-11-03T08:00:00"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "task-example",
    "status": "finished",
    "created_time": "2026-11-03T08:00:00",
    "progress": 100,
    "files": [
      {
        "file_url": "https://example.com/result.png",
        "file_type": "image"
      }
    ]
  }
}

Complete runnable polling example

Expand for the same payload end to end, including business-code, missing-task-ID, failed-state, unexpected-state, and network-error handling.

Complete runnable polling example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "blackforestlabs/flux-3-klein/edit",
  "input": {
    "prompt": "Keep the sneaker from the first image exactly as it is and place it on a snowy wooden porch step with soft winter daylight.",
    "size": "1:1",
    "resolution": "1K",
    "n": 1,
    "output_format": "png",
    "enable_safety_checker": true,
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-3-klein/edit/v1/01/input-01-product-placeholder.png"
    ]
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

while true; do
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep 2
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters

This table lists only public fields inside input. See Quick Start for top-level model and optional callback_url usage.

Field	Type	Required	Default	Description
input.prompt	string	Yes	–	Non-blank edit instruction. Refer to inputs by order, for example the first image.
input.image_urls	string[]	Yes	–	1–10 public HTTP(S) image URLs, in the order the prompt refers to them.
input.size	string	No	1:1	Preset 1:1, 4:3, 3:4, 16:9, 9:16, 3:2 or 2:3 (long edge set by resolution), or WIDTHxHEIGHT with each side 256–4096 in multiples of 16.
input.resolution	string	No	1K	1K, 2K or 4K; presets use a long edge of 1024, 2048 or 4096. A custom size must send the tier of its longer side: ≤1024 → 1K, ≤2048 → 2K, otherwise 4K.
input.n	integer	No	1	Number of images, integer 1–4.
input.output_format	string	No	png	png, jpeg or webp.
input.enable_safety_checker	boolean	No	true	Boolean. Turns the upstream safety checker on or off.

Response Fields

The submit response identifies the task. The status response supplies result files or failure details at a terminal state.

Field	Type	Description
code	integer	Business response code; 0 or 200 indicates success.
message	string	Optional human-readable response message.
data.task_id	string	Unique task ID used for status queries after submission.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation timestamp.
data.progress	integer	Progress from 0–100 in status responses.
data.files[]	array	Generated files in returned order when finished.
data.files[].file_url	string	Direct URL of the generated file (.png).
data.files[].file_type	string	Result files are identified as image.
data.error_message	string \| null	Readable failure reason for failed tasks.

Task Lifecycle

Only the first two states may be polled again. finished and failed are terminal.

not_started
Accepted and queued; wait before checking again.
running
Generation is in progress; continue polling.
finished
Successful terminal state; validate files and read file URLs.
failed
Failure terminal state; read error_message and stop. Reserved credits are refunded in full.

Polling and Errors

AuthenticationKeep a valid VIDGO_API_KEY on the server and send requests with Bearer authentication.
Validation400 indicates an invalid model ID, field, enum, length, count or size for this endpoint, including fields that belong to another endpoint.
Polling intervalStart at 2–5 seconds, use exponential backoff for 429/5xx, and enforce an overall timeout.
Terminal statesRead file URLs from files after finished, or error_message after failed. Both states end polling.
Callback optionProvide a public top-level callback_url to receive the task object after finished or failed.
Network errorsDistinguish request timeout, network failure, and task failure. Retry the same query only when safe.

Model Specifications

Specification	Value	Details
Model	blackforestlabs/flux-3-klein/edit	FLUX 3 Klein Edit
Input	prompt + image_urls (1–10)	Images referred to by order
Output	PNG / JPEG / WebP × n (1–4)	Image URLs in files[]
resolution	1K / 2K / 4K	1.8 / 2.8 / 7.2 credits per image
size	7 presets or WIDTHxHEIGHT	256–4096 px per side, multiples of 16

View the FLUX 3 Klein Edit API docs

FLUX 3 Klein Edit

FLUX 3 Klein Edit uses the same compact 5.6B-parameter FLUX 3 model from Black Forest Labs for instruction-based editing and multi-image composition. Send one to ten images in image_urls, refer to them by order in the prompt, and receive one to four results in PNG, JPEG or WebP. Input images are not billed, so a ten-image composite costs the same 1.8 credits at 1K as a single edit.

Why Choose FLUX 3 Klein Edit?

Up to ten input imagesCombine a person, a garment, a product and a setting from separate images in one instruction.
Edits priced like generation1.8, 2.8 or 7.2 credits per output image at 1K, 2K or 4K; the number of input images does not change the price.
Plain-language instructionsDescribe the change and refer to inputs as the first, second or third image; no masks are needed.
Flexible output sizeUse a preset ratio or an exact WIDTHxHEIGHT so the edited image fits its destination.
Batch variationsRequest up to four results per call to compare different takes on the same edit.

Parameters

Parameter	Requirement	Description
prompt	Required	Non-blank edit instruction. Refer to inputs by order, for example the first image.
image_urls	Required	1–10 public HTTP(S) image URLs, in the order the prompt refers to them.
size	Optional	Preset 1:1, 4:3, 3:4, 16:9, 9:16, 3:2 or 2:3 (long edge set by resolution), or WIDTHxHEIGHT with each side 256–4096 in multiples of 16. Default`1:1`
resolution	Optional	1K, 2K or 4K; presets use a long edge of 1024, 2048 or 4096. A custom size must send the tier of its longer side: ≤1024 → 1K, ≤2048 → 2K, otherwise 4K. Default`1K2K4K`
n	Optional	Number of images, integer 1–4. Default`1`
output_format	Optional	png, jpeg or webp. Default`pngjpegwebp`
enable_safety_checker	Optional	Boolean. Turns the upstream safety checker on or off. Default`true`

How to Use

Collect the inputsGather one to ten public image URLs and order them the way you will mention them.
Write the instructionName what to keep from each image and what to change, for example keep the face from the first image.
Set size and resolutionPick a ratio and tier, or an exact size with the matching resolution.
Submit and collectSend model blackforestlabs/flux-3-klein/edit, poll with the task_id and read the results from files.

Usage and Pricing

Billed per output image by resolution. Total credits = rate × n. 1 credit = $0.005.

Generation and editing cost the same, and input images are not billed. Credits are reserved on submission and refunded in full if the task fails. Example: 4 images at 2K = 11.2 credits ($0.056).

Usage and Pricing
Option	Credits / image	USD / image
1K	1.8	$0.009
2K	2.8	$0.014
4K	7.2	$0.036

Best Use Cases

Seasonal background swapsKeep a product exactly as photographed and move it into a winter, summer or holiday scene.
Outfit and accessory try-onDress a model in a garment from another photo while keeping face and pose.
Interior restylingChange furniture, materials or lighting in a room photo while the layout stays.
Composite marketing visualsCombine a product, a person and a location from separate shoots into one ad image.

Pro Tips

Give each input a role in the prompt: keep the person from the first image, the jacket from the second, the street from the third.
Put the most important image first; order is how the model knows which picture you mean.
Say explicitly what must not change, such as face, logo placement or product shape.
Test the instruction at 1K, then rerun at 2K or 4K for delivery.

Notes

image_urls must contain 1–10 public HTTP(S) URLs.
Input images are not billed; credits depend only on resolution and n.
A custom size must be sent with the resolution of its longer side (≤1024 → 1K, ≤2048 → 2K, otherwise 4K).

Related Models

GPT Image 2.6 Flare Text to Image preview

GPT Image 2.6 Flare Text to ImageGPT Image 2.6 Flare Text to Image turns text prompts into 1K–4K images with fast low-quality drafts, legible poster typography and transparent backgrounds. It places headlines, subjects and props where the prompt puts them, so one prompt carries a concept from quick draft to final quality.

GPT Image 2.6 Flare Image EditGPT Image 2.6 Flare Image Edit turns 1–16 reference images and text instructions into a new 1K–4K image, with optional masks, transparent cutouts and adjustable planning effort. It keeps the first image’s aspect ratio by default, and keep-and-change instructions let it recolor or relight a subject while the rest holds.

GPT Image 2.6 Sunburst Text to Image preview

GPT Image 2.6 Sunburst Text to ImageGPT Image 2.6 Sunburst Text to Image turns detailed text prompts into 1K–4K images with fine material texture, crowded multi-element layouts and quality up to max. It keeps long scene descriptions in order, placing subjects, props and light where the prompt puts them.

GPT Image 2.6 Sunburst Image Edit preview

GPT Image 2.6 Sunburst Image EditGPT Image 2.6 Sunburst Image Edit turns 1–16 reference images and text instructions into a refined 1K–4K image, with masks, multi-image composites and quality up to max. Built for stronger consistency across edits, it keeps identity, materials and lighting steady while applying the requested change.

Ideogram Vector 1.0 Text to Vector preview

Ideogram Vector 1.0 Text to VectorIdeogram Vector 1.0 Text to Vector turns a written prompt into SVG artwork for logos, icons and illustrations, with up to five reference images and 17 aspect ratios plus auto. Results are true vector files that scale cleanly from favicon to billboard.

Ideogram Vector 1.0 Image to Vector preview

Ideogram Vector 1.0 Image to VectorIdeogram Vector 1.0 Image to Vector turns one raster image into an SVG file, with a detailed default mode and a simple mode that uses fewer shapes. It follows the shapes and colours of the source so logos, sketches and illustrations become scalable artwork.

FLUX 3 Klein Text to ImageFLUX 3 Klein Text to Image turns prompts into product shots, scenes and illustrations at 1K, 2K or 4K, with seven presets, exact custom sizes and up to four images per call. It keeps per-image cost low so you can iterate widely before rendering finals.

Nano Banana 2.1 Text to ImageNano Banana 2.1 Text to Image turns text prompts into 1K–4K images with text layout rendering and panoramic compositions. It preserves perspective and lighting while eliminating tiling artifacts in panoramic aspect ratios.

Nano Banana 2.1 EditNano Banana 2.1 Edit uses 1–10 reference images for image blending and local edits, with consistent characters and sharp redraws. It preserves character appearance and lighting as elements change, delivering crisp results at up to 4K resolution.

Ideogram 4.5 Text to ImageIdeogram 4.5 Text to Image turns written prompts into posters, wordmarks and text-rich images, with three quality tiers and 1–8 images per request. It keeps headlines and short copy legible while you pick the aspect ratio or one of 36 exact pixel sizes.

Ideogram 4.5 EditIdeogram 4.5 Edit turns one source image and a written instruction into a revised image, with optional masks, up to four reference images and high edit precision. It keeps the areas you did not ask to change, so repeated edits stay close to the original.

Qwen Image 2.1 Text to ImageQwen Image 2.1 Text to Image turns text into native 1K and 2K images with RGBA transparency and Chinese-English typography. It preserves lighting, composition, and aspect ratios while delivering clean transparent layers that need no background removal.

Qwen Image 2.1 EditQwen Image 2.1 Edit turns 1-10 reference images and instructions into precise edits, with multi-image feature fusion and masked inpainting. It preserves facial features and product materials while replacing backgrounds naturally and retaining every pixel outside the mask.

Seedream 5.0 Flash Text to Image preview

Seedream 5.0 Flash Text to ImageSeedream 5.0 Flash Text to Image turns text prompts into high-definition 1K to 2K images, with Chinese and English text layout and 8 aspect ratios. It closely follows complex prompts while providing fine control over lighting and composition.

Seedream 5.0 Flash Image EditSeedream 5.0 Flash Image Edit combines 1 to 10 reference images with a prompt to create new work at up to 2K resolution. It closely preserves faces, clothing and composition from the source images while naturally transforming their style.

GPT Image 2.5 Flare Text to Image preview

GPT Image 2.5 Flare Text to ImageGPT Image 2.5 Flare Text to Image turns text prompts into detailed 1K–4K images, with transparent backgrounds and low latency. It combines fast responses with natural lighting while avoiding structural distortion in large images.

FLUX 3 Klein Edit API FAQ

What is the FLUX 3 Klein Edit API?

FLUX 3 Klein Edit is a Black Forest Labs model for editing and combining images with written instructions. It takes one to ten input images and returns one to four edited results at 1K, 2K or 4K in PNG, JPEG or WebP, priced the same as generation. Built on the compact FLUX 3 Klein model, it keeps the subjects you name from each input while changing scenes, outfits, materials or style. You can call it programmatically or try it from the playground above.

How many images can FLUX 3 Klein Edit combine?

Between 1 and 10 images in image_urls. Refer to them by order in the prompt so the model knows which subject comes from which picture.

How much does FLUX 3 Klein Edit cost?

Per output image: 1K 1.8 credits ($0.009), 2K 2.8 credits ($0.014) and 4K 7.2 credits ($0.036), the same as text-to-image. Input images are not charged.

How should I write prompts for FLUX 3 Klein Edit with several images?

Assign each image a role, for example keep the person from the first image, use the jacket from the second and place them on the street from the third. State what must stay unchanged.

Does FLUX 3 Klein Edit need a mask?

No. Edits are driven by the instruction alone. For mask-based region edits, use Ideogram 4.5 Edit.

Which sizes can FLUX 3 Klein Edit output?

Presets 1:1, 4:3, 3:4, 16:9, 9:16, 3:2 and 2:3, or WIDTHxHEIGHT with sides 256–4096 px in multiples of 16, sent with the resolution of its longer side.

Can FLUX 3 Klein Edit return several variations?

Yes. Set n from 1 to 4; each result is billed at the selected resolution rate.