blackforestlabs/flux-kontext-proFlux Kontext Pro Edit transforms images via natural language instructions, enabling mask-free edits and targeted text replacement. It preserves source facial identity and lighting direction while applying precise alterations.
Get API KeyGenerated images will appear here
Estimated cost: 8 credits · $0.040
8 credits ($0.040) per generation.
Replace the painted name on the bow "MARISOL" with "ALBATROS". Paint the new letters in the same hand-painted white capital lettering style, same size, same brush texture, with the same chipping and weathering as the rest of the hull. Keep everything else unchanged: the boat, its sky blue hull and white stripe, the rope and buoy, the pebble beach, the palafito stilt houses, the hills, the overcast light and the camera framing.
Change the time of day from bright midday to late night. The only light source is now a single old tin oil lantern with a warm flickering flame, placed on the ground to the left of the woman, casting warm orange light across her face, hands and the textile and long soft shadows on the wall. The sky above the courtyard becomes deep navy with a few stars, the turquoise door and bougainvillea fall mostly into shadow. Keep everything else exactly the same: the woman's face, expression, pose, braid with red ribbons, embroidered huipil, the exact position of her hands on the batten, the diamond pattern of the textile, the loom, the post, the clay jar and the camera framing.
Remove the stacked white plastic chairs, the yellow bucket, the grey mop and the green garden hose. Fill in the areas behind them with the matching zellige mosaic fountain tiles and patterned floor tiles, continuing the existing geometric pattern and the diagonal late-afternoon light and shadows. Keep the fountain, the water, the arches, the carved balconies, the orange trees in terracotta pots and the camera framing exactly the same.
REST API
This flow submits one valid Flux Kontext Pro Edit request, captures its task_id, and reads image URLs after the asynchronous task ends.
Create an API key, keep it on the server, and send it as Authorization: Bearer VIDGO_API_KEY.
https://api.vidgo.ai/api/generate/submitSend the current model ID, prompt, and one source image URL to the unified submit endpoint. The example keeps only first-call fields.
curl --request POST \
--url "https://api.vidgo.ai/api/generate/submit" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"model": "blackforestlabs/flux-kontext-pro",
"input": {
"prompt": "Replace the painted name on the bow \"MARISOL\" with \"ALBATROS\". Paint the new letters in the same hand-painted white capital lettering style, same size, same brush texture, with the same chipping and weathering as the rest of the hull. Keep everything else unchanged: the boat, its sky blue hull and white stripe, the rope and buoy, the pebble beach, the palafito stilt houses, the hills, the overcast light and the camera framing.",
"image_urls": [
"https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-kontext-pro/v1/02/input-01.png"
],
"size": "16:9",
"output_format": "jpg"
}
}'Read data.task_id and poll only while status is not_started or running. Stop on both finished and failed.
GET https://api.vidgo.ai/api/generate/status/{task_id}Poll every 2–5 seconds and back off on 429/5xx. Or provide top-level callback_url to receive a terminal-state callback.
not_startedrunningfinishedfailed{
"code": 200,
"data": {
"task_id": "KH8OWRITIOASWYGA",
"status": "running",
"created_time": "2026-09-26T11:02:37"
}
}{
"code": 200,
"data": {
"task_id": "KH8OWRITIOASWYGA",
"status": "finished",
"files": [
{
"file_type": "image",
"file_url": "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-kontext-pro/v1/02/output.jpg"
}
],
"created_time": "2026-09-26T11:02:37",
"error_message": null,
"progress": 100
}
}Expand for the same payload end to end, including business-code, missing-task-ID, failed-state, unexpected-state, and network-error handling.
set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"
REQUEST_BODY=$(cat <<'JSON'
{
"model": "blackforestlabs/flux-kontext-pro",
"input": {
"prompt": "Replace the painted name on the bow \"MARISOL\" with \"ALBATROS\". Paint the new letters in the same hand-painted white capital lettering style, same size, same brush texture, with the same chipping and weathering as the rest of the hull. Keep everything else unchanged: the boat, its sky blue hull and white stripe, the rope and buoy, the pebble beach, the palafito stilt houses, the hills, the overcast light and the camera framing.",
"image_urls": [
"https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-kontext-pro/v1/02/input-01.png"
],
"size": "16:9",
"output_format": "jpg"
}
}
JSON
)
SUBMIT_RESPONSE=$(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
doneThis 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 | – | Describe the requested image changes using 1–2,000 characters, including at least one non-whitespace character. |
| input.image_urls | string[] | Yes | – | Provide exactly 1 publicly accessible HTTP(S) image URL as the source image. Enter a URL or upload an image. |
| input.size | string | No | 1:1 | Output aspect ratio. Defaults to 1:1. 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, 9:21. |
| input.output_format | string | No | – | Output image file format: png or jpg. png, jpg. |
The submit response identifies the task. The status response supplies image 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 generated-image URL. |
| data.files[].file_type | string | Image results are identified as image. |
| data.files[].watermark_url | string | null | Optional watermarked-file URL when present. |
| data.error_message | string | null | Readable failure reason for failed tasks. |
Only the first two states may be polled again. finished and failed are terminal.
not_startedAccepted and queued; wait before checking again.
runningImage generation is in progress; continue polling.
finishedSuccessful terminal state; validate files and read image URLs.
failedFailure terminal state; read error_message and stop.
| Specification | Value | Details |
|---|---|---|
| Model | blackforestlabs/flux-kontext-pro | Edit one source image using text instructions. |
| size | 1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 21:9 / 9:21 | Default: 1:1 |
| output_format | png / jpg | Output image file format. |
Flux Kontext Pro Edit is a Black Forest Labs model for high-precision instruction-based image editing. It modifies source images according to natural-language prompts, featuring mask-free targeted editing, seamless in-image text replacement, and rapid 5–6 second inference speeds. Built on an in-context flow-matching transformer architecture, it preserves the reference subject's identity, composition, and illumination while executing requested changes. You can call it programmatically or try it from the playground above.
No. Flux Kontext Pro Edit relies on an in-context visual understanding architecture that identifies which regions to modify purely from your text prompt, eliminating the need to paint or upload selection masks.
The model preserves character consistency by conditioning on the source image tokens throughout the generative flow. Adding explicit prompt clauses such as while keeping the exact face, skin tone, and hairstyle provides optimal identity retention.
Yes. It is engineered for text modification on signs, posters, and packages. Enclose both the original and replacement text in quotes within the prompt, for example Replace 'SALE' with 'NEW', and mention keeping the existing font style.
You can supply standard web formats including JPG, JPEG, PNG, and WEBP via a publicly accessible HTTP or HTTPS URL in the image_urls array. Clear, well-lit reference images yield the highest editing precision.
Yes. You can take the resulting image URL from your first edit and submit it as the source image in your next request, enabling multi-step creative refinement while preserving cumulative visual coherence.
Flux Kontext Pro Edit is the ideal choice for single-image background swaps. At 8 credits per generation and 5–6 second execution, it effortlessly replaces surroundings while maintaining subject positioning and blending natural lighting.
