FLUX.2 Flex Text to Image API

blackforestlabs/flux-2-flex/text-to-image

1K/2K · 8 sizes

FLUX.2 Flex Text to Image transforms natural prompts into intricate visual compositions with micro-surface textures and Hex color control. It preserves multi-subject spatial balance while rendering natural lighting dynamics.

Get API Key

Input

PromptRequired0/5000

SizeRequired

ResolutionRequired

OutputIdle

Generated images will appear here

Estimated Cost: —

Continue Using

FLUX.2 Flex Edit FLUX.2 Pro Text to Image FLUX.2 Pro Edit Flux Kontext Pro Text to Image

Examples

A photorealistic mid shot of a weathered larch-wood trail signpost at a high Alpine mountain pass in late afternoon. One small square metal plate at the top of the post and three arrow-shaped boards below it, each with crisp carved, white-painted capital lettering. Each board carries only its own single line of text, and nothing is repeated anywhere else: Top square plate: "SENTIERO 443" Top arrow, pointing left: "RIFUGIO NUVOLAU 1 h 20" Middle arrow, pointing right: "PASSO GIAU 45 min" Bottom arrow, pointing left: "LAGO FEDERA 1 h 50" The wood shows deep silver-grey grain, cracks, rusted bolts and patches of orange and pale-green lichen. Behind the post, jagged dolomite peaks glow pink in alpenglow above a scree slope, and a narrow dirt path leads away with two tiny out-of-focus hikers. Low warm sun from the right, shallow depth of field on the signs, 50mm lens. Lettering sharp and correctly spelled, no other words or numbers, no logos, no watermark.

A cinematic view from the pilot's seat of a retro-futurist research spacecraft cockpit in orbit above the night side of Earth. A curved instrument console spans the frame, built from brushed aluminium, olive-green enamel panels and chunky toggle switches with metal guards. Only four backlit amber labels appear on the console, each exactly once: on the far left panel "O2 21.4%", above a round analog gauge left of centre "COOLANT °C" with the needle at 22, directly right of the central screen "NAV LOCK", and on the far right panel "DOCK 14.2 m/s". All other switches and panels are unlabeled. The central small green monochrome screen shows a wireframe orbit trace with no text. Through the wide front window, city lights trace coastlines on the dark Earth below and a thin blue atmospheric line glows along the horizon. The pilot's gloved hands rest near a throttle lever at the bottom edge. Subtle scratches, worn paint around the switches and dust drifting in the soft cabin light. Sharp, legible labels in a clean engineering typeface, physically plausible lighting, no other text, no logos, no watermark.

REST API

Quick Start

This flow submits one valid FLUX.2 Flex Text to Image request, captures its task_id, and reads image 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 image task

Send the current model ID, prompt, size, and resolution to the unified submit endpoint.

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-2-flex/text-to-image",
  "input": {
    "prompt": "An overhead photograph of an open naturalist's field notebook lying on a sun-warmed basalt rock beside a tide pool. The two cream, lightly textured pages are filled with delicate pencil and watercolour studies: on the left page a purple ochre sea star, a giant green anemone with open tentacles, and a hermit crab in a turban-snail shell; on the right page a cluster of goose barnacles, a small tidepool sculpin, and a strand of rockweed. Each drawing has a neat handwritten ink label: \"Pisaster ochraceus\", \"Anthopleura xanthogrammica\", \"Pagurus samuelis\", \"Pollicipes polymerus\", \"Oligocottus maculosus\", \"Fucus distichus\". Across the top of the left page, the handwritten heading reads exactly \"LOW TIDE 0.3 m - 14 MAY\". Small measurement ticks and fine arrows point to anatomical details. A graphite pencil, a small brass magnifier and a water brush rest on the pages; a few drops of seawater and grains of sand sit near the paper edge. Soft overcast light, true-to-life paper texture, visible watercolour blooms and pencil grain, legible correctly spelled handwriting, no other text, no logos, no watermark.",
    "size": "4:3",
    "resolution": "1K"
  }
}'

Wait for the image 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": "SBR3R4D3GOFPXM1Z",
    "status": "running",
    "created_time": "2026-09-26T11:07:50"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "SBR3R4D3GOFPXM1Z",
    "status": "finished",
    "files": [
      {
        "file_type": "image",
        "file_url": "https://cdn.vidgo.ai/apis/models/blackforestlabs/flux-2-flex/text-to-image/v1/02/output.jpg"
      }
    ],
    "created_time": "2026-09-26T11:07:50",
    "error_message": null,
    "progress": 100
  }
}

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-2-flex/text-to-image",
  "input": {
    "prompt": "An overhead photograph of an open naturalist's field notebook lying on a sun-warmed basalt rock beside a tide pool. The two cream, lightly textured pages are filled with delicate pencil and watercolour studies: on the left page a purple ochre sea star, a giant green anemone with open tentacles, and a hermit crab in a turban-snail shell; on the right page a cluster of goose barnacles, a small tidepool sculpin, and a strand of rockweed. Each drawing has a neat handwritten ink label: \"Pisaster ochraceus\", \"Anthopleura xanthogrammica\", \"Pagurus samuelis\", \"Pollicipes polymerus\", \"Oligocottus maculosus\", \"Fucus distichus\". Across the top of the left page, the handwritten heading reads exactly \"LOW TIDE 0.3 m - 14 MAY\". Small measurement ticks and fine arrows point to anatomical details. A graphite pencil, a small brass magnifier and a water brush rest on the pages; a few drops of seawater and grains of sand sit near the paper edge. Soft overcast light, true-to-life paper texture, visible watercolour blooms and pencil grain, legible correctly spelled handwriting, no other text, no logos, no watermark.",
    "size": "4:3",
    "resolution": "1K"
  }
}
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 the fields inside input. See Quick Start for top-level model and optional callback_url usage.

Field	Type	Required	Default	Description
input.prompt	string	Yes	–	Detailed text prompt describing subjects, micro-textures, styling, and quoted text strings. Accepts 3 to 5,000 characters.
input.size	string	Yes	–	Target aspect ratio preset. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, auto.
input.resolution	string	Yes	–	Output rendering resolution: 1K standard HD or 2K ultra-high resolution up to 4MP.

Response Fields

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.

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
Image generation is in progress; continue polling.
finished
Successful terminal state; validate files and read image URLs.
failed
Failure terminal state; read error_message and stop.

Polling and Errors

AuthenticationKeep a valid VIDGO_API_KEY on the server and send requests with Bearer authentication.
Validation400 indicates that the model ID, fields, enums, or length differ from the parameter table.
Polling intervalStart at 2–5 seconds, use exponential backoff for 429/5xx, and enforce an overall timeout.
Terminal statesRead image URLs from files after finished, or error_message after failed. Both states end polling.
Callback optionProvide a public top-level callback_url to receive a flat 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-2-flex/text-to-image	Text-to-image generation.
prompt	3–5,000	Characters.
size	1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 3:2 / 2:3 / auto	Output aspect ratio.
resolution	1K / 2K	Output image resolution.

FLUX.2 Flex Text to Image API documentation

FLUX.2 Flex Text to Image

FLUX.2 Flex Text to Image is Black Forest Labs high-flexibility visual synthesis model designed for intricate textures and artistic typography. Powered by the FLUX.2 architecture and a 24B Mistral-3 visual language model, it interprets complex multifaceted prompts with elevated spatial fidelity, delivering outputs up to 2K resolution starting at 18 credits ($0.090).

Why Choose FLUX.2 Flex Text to Image?

Granular Micro-Surface TexturesExcels at depicting fine physical nuances such as woven cloth weave, aged parchment, metallic brushed finishes, and complex organic foliage.
Hex Color PrecisionAdhere strictly to corporate palette guidelines by directly specifying hexadecimal color codes in prompts, eliminating unintended color drift.
Intricate Typography RenderingEnclose phrases in double quotes to generate precise, beautifully aligned English text directly onto artistic signs, book covers, and packaging.
Multi-Subject Compositional BalanceLeverage the 24B Mistral-3 VLM to resolve complex multi-character scenes, spatial depth, and realistic lighting reflections.
Ultra-High 2K ResolutionRender up to 4MP images across 8 aspect ratios, delivering superior edge definition and rich depth for high-end digital publishing.

Parameters

Parameter	Requirement	Description
prompt	Required	Detailed text prompt describing subjects, micro-textures, styling, and quoted text strings. Accepts 3 to 5,000 characters.
size	Required	Target aspect ratio preset. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, auto. `1:14:33:416:99:163:22:3auto`
resolution	Required	Output rendering resolution: 1K standard HD or 2K ultra-high resolution up to 4MP. `1K2K`

How to Use

Draft Prompt & Surface DetailsDetail subject geometry, micro-textures, lighting direction, Hex color values, and quote-enclosed lettering.
Select Ratio & ResolutionChoose from 8 aspect ratio presets and specify 1K standard or 2K ultra-high resolution based on intended distribution.
Submit Generation TaskDispatch an authorized POST request to the Flex text-to-image endpoint and capture the returned task_id.
Poll for CompletionQuery the task status endpoint at periodic intervals until the status advances from running to finished.
Retrieve High-Fidelity AssetDownload the generated image URL from the completed payload or receive it asynchronously via callback_url.

Pricing

Flexible pay-per-request pricing reflecting specialized high-detail rendering compute, with full automatic refund protection.

Tier	Rate	Details
1K Standard Resolution	18 credits / run · $0.090	Covers high-detail rendering across all 8 aspect ratios at 1K resolution
2K Ultra-High Resolution	27 credits / run · $0.135	Delivers up to 4MP output with razor-sharp micro-textures and intricate fine details

Best Use Cases

Luxury Packaging & BrandingRender bespoke consumer packaging with embossed typography, gold leaf accents, and exact corporate Hex color codes.
Digital Concept Art & World-BuildingCreate sprawling fantasy landscapes, sci-fi interiors, and character concepts with complex atmospheric scattering and lighting.
Editorial Magazine & Book CoversGenerate visually arresting print-ready cover illustrations incorporating styled headline titles and rich textural backgrounds.
Architectural Material ExplorationVisualize interior concepts highlighting authentic finishes like brushed concrete, oiled walnut, and fluted glass partitions.

Pro Tips

Enclose Key Words in Quotes：Place exact lettering inside double quotation marks to guide letterforms and prevent spelling distortions.
Incorporate Hex Color Values：Include explicit hexadecimal codes (e.g., #D4AF37 for metallic gold) to achieve repeatable and strict color compliance.
Describe Material Tactility：FLUX.2 Flex is optimized for sensory descriptors; detail tactile surfaces like 'matte ceramic glaze' or 'raw unbleached linen'.
Leverage 2K for Fine Printing：Always choose 2K resolution when generating assets destined for physical print, exhibition, or high-density monitors.
Set Up Webhook Notifications：Provide a callback_url in production integrations to receive instant HTTP notifications once rendering finishes.

Notes

Prompt Length Range：The prompt field must contain between 3 and 5,000 characters and include at least one non-whitespace character.
Dedicated Text Generation：This endpoint accepts text prompts only; for multi-image reference workflows, please use FLUX.2 Flex Edit.
Asynchronous Processing Pipeline：Requests are queued asynchronously and transition from not_started to running before reaching finished.
Automatic Balance Refund：In the event of an unexpected timeout or service failure, reserved credits are immediately and fully restored.

Related Models

Grok Imagine Image 2.0 Text to Image preview

Grok Imagine Image 2.0 Text to ImageGenerate crisp, high-fidelity images up to 2K from text prompts with Grok Imagine Image 2.0. Features designer-grade typography, precise prompt adherence, and versatile aspect ratios.

Grok Imagine Image 2.0 EditGenerate crisp, high-fidelity images up to 2K from text prompts with Grok Imagine Image 2.0. Features designer-grade typography, precise prompt adherence, and versatile aspect ratios.

Qwen Image 3.0 Text-to-ImageAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Image EditAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Pro Text-to-Image preview

Qwen Image 3.0 Pro Text-to-ImageAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Pro Image EditAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Seedream 5.0 Pro Text-to-ImageThe ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.

Seedream 5.0 Pro Image EditThe ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.

Nano Banana 2 Lite Text to Image preview

Nano Banana 2 Lite Text to ImageGenerate crisp 1K images in ~4 seconds from text prompts with Nano Banana 2 Lite. Optimized for high-volume rapid iteration, in-image text in 25+ languages, and 10 aspect ratios at $0.025 per generation.

Nano Banana 2 Lite EditGenerate crisp 1K images in ~4 seconds from text prompts with Nano Banana 2 Lite. Optimized for high-volume rapid iteration, in-image text in 25+ languages, and 10 aspect ratios at $0.025 per generation.

Grok Imagine Image Quality Text to Image preview

Grok Imagine Image Quality Text to ImageGenerate high-fidelity images up to 2K resolution from text prompts with Grok Imagine Image Quality. Features photorealistic detail, sharp text rendering, and 5 aspect ratios.

Grok Imagine Image Quality EditGenerate high-fidelity images up to 2K resolution from text prompts with Grok Imagine Image Quality. Features photorealistic detail, sharp text rendering, and 5 aspect ratios.

GPT Image 2 Text-to-ImageOpenAI image generation and editing with quality tiers, flexible size controls, and single-image outputs up to 4K.

GPT Image 2 Image EditOpenAI image generation and editing with quality tiers, flexible size controls, and single-image outputs up to 4K.

Wan 2.7 Image Standard Text to Image preview

Wan 2.7 Image Standard Text to ImageCreate and edit images from prompts or reference photos with Wan 2.7 Image Standard and Pro models.

Wan 2.7 Image Standard EditCreate and edit images from prompts or reference photos with Wan 2.7 Image Standard and Pro models.

FLUX.2 Flex Text to Image API FAQ

What is the FLUX.2 Flex Text to Image API?

FLUX.2 Flex Text to Image is a specialized visual generation model developed by Black Forest Labs. It translates natural language prompts into intricate compositions up to 2K resolution, excelling in micro-surface textures, Hex color accuracy, and native English typography. Powered by a 32B flow matching architecture and a 24B Mistral-3 visual language model, it balances spatial coherence with high artistic flexibility. You can call it programmatically via the API or test prompts in the playground above.

How does FLUX.2 Flex differ from FLUX.2 Pro for text-to-image?

While FLUX.2 Pro is tailored for photorealistic fidelity, fast turnaround, and cost efficiency at 6 credits per run, FLUX.2 Flex provides enhanced creative latitude for granular micro-textures, complex artistic layouts, and bespoke tactile rendering at 18 credits per run.

Can I use Hex color codes with FLUX.2 Flex Text to Image?

Yes. FLUX.2 Flex natively recognizes standard hexadecimal color codes (such as #2B5797) within prompts, ensuring generated packaging, fabrics, and backgrounds faithfully match your defined brand color specifications.

Does FLUX.2 Flex Text to Image support native English text rendering?

Yes. By surrounding your target wording in double quotation marks (for example "SUMMIT 2026"), the model will cleanly render crisp, legible English characters onto posters, storefronts, and signage.

What are the pricing rates for FLUX.2 Flex Text to Image?

Standard 1K resolution generation costs 18 credits ($0.090) per task, and 2K ultra-high resolution costs 27 credits ($0.135) per task. There are no recurring monthly minimums or upfront licensing fees.

What aspect ratios are supported by FLUX.2 Flex Text to Image?

The size parameter accepts 8 presets: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, and auto. You can adapt dimensions for social media verticals, wide banners, or square product displays.

What happens if a FLUX.2 Flex generation task fails?

All tasks are protected by an automatic refund policy. If a generation request encounters an error or processing timeout, the pre-deducted credits are immediately returned in full to your account.