Bria

FIBO 1.5

fibo-gen-1.5/text-to-image

BRIA's 8B flow-matching DiT distilled image model generates images with just 4 to 6 sampling steps and supports JSON-structured prompts with attribute-decoupled editing

fibo-edit-1.5/image-to-image fibo-gen-1.5/text-to-image

Try fibo-gen-1.5/text-to-image

Input

Showcases

View all showcases

Output

image

Fill in the parameters and run — results show up here.

Pricing

fibo-gen-1.5/text-to-image per image

Unit Price	$0.0575

Positioning Overview

fibo-gen-1.5 is the text-to-image line in the fibo-1.5 family, aimed at developers who need professional-grade controllability and reproducibility. It is built on an 8B-parameter DiT with a flow-matching architecture and uses few-step distilled sampling, requiring only 4–6 steps at CFG=1.0 to complete inference. It also continues the structured long-prompt paradigm and follows attributes such as lighting, composition, color, and camera relatively well. It is suited to image-production scenarios that bring batch generation, attribute-level iteration, and result reproducibility into engineering workflows.

Core Highlights

Few-step sampling dramatically reduces per-image inference cost — after distillation, only 4–6 steps are needed with no classifier-free guidance, making calls cheaper than traditional high-CFG multi-step pipelines.
Structured long prompts deliver strong prompt adherence — generation is driven by long descriptions that separately specify the subject, lighting, composition, color, camera, and other attributes, giving clearer controllability in professional scenarios.
Reproducible generation results — the seed defaults to a fixed value of 5555; the same seed and prompt reproduce the same image, which facilitates batch pipelines and regression verification.
Division of labor between text-to-image and image editing within the family — the same family also includes the fibo-edit-1.5 image-editing line; switch to that line when you need to edit images based on reference images.

Capability Details

Few-step distilled sampling: images can be generated with the recommended settings of 4–6 steps and CFG=1.0, eliminating the tuning effort and compute consumption of traditional high-CFG workflows and returning usable results faster per request.

Structured prompt adherence: training and inference are based on structured long descriptions of roughly a thousand words; when developers spell out attributes such as subject, lighting, composition, and camera item by item, the resulting image more closely matches expectations.

Reproducible generation: the seed parameter and the prompt together determine the output; fixing both reproduces the same image, making it suitable for version comparison and result tracing in batch production.

Multiple aspect ratios: nine ratios are built in — 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, and 16:9 — so you can select one directly according to the placement or layout, reducing post-processing crops.

Long prompt input: the prompt supports up to 10,000 characters, so structured long descriptions can be written in full without being compressed into short sentences, allowing fuller attribute expression.

Use Cases

Commercial visual designers: image generation with structured long prompts — write lighting, composition, color, and camera into the prompt item by item to produce commercial-grade images directly usable for advertising and e-commerce materials.
Creative teams: attribute-level iterative refinement — fix the seed and change only a single attribute to regenerate repeatedly, producing a series of variants for option comparison and reducing rework from rewriting entire prompts.
Engineering teams: batch reproducible image generation — call in batches with a fixed seed and templated long prompts to produce style-consistent, traceable image assets for content-production pipelines.
Application developers: multi-ratio adapted generation — select the aspect ratio according to the target layout and generate images directly embeddable in apps, web pages, and video thumbnails.

Limitations and Selection Advice

Negative prompts have no effect in this version, so the image must be constrained entirely through positive descriptions; per the official documentation, weights do not apply to fine-tuning. Continuing to use legacy high-CFG multi-step workflows will deviate from the expected results; use CFG=1.0 with 4–6 steps. The controllability advantage depends on structured long prompts, and ordinary short prompts yield limited benefit. The 8B scale is demanding for local consumer-grade hardware, and local deployment requires a quantized version; calling it on HiAPI.ai avoids this issue.

Create a generation task

POST https://api.hiapi.ai/v1/tasks

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: fibo-gen-1.5/text-to-image

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for fibo-gen-1.5/text-to-image and route default — see the parameter table below.

seedintegerOptionalDefault: 5555

Random seed, default 5555; the same seed with the same prompt reproduces the same image.

promptstringRequiredminLength 1maxLength 10000

Text description of the image to generate, i.e., the text-to-image prompt.

aspect_ratiostringOptionalDefault: "1:1"

Aspect ratio of the output image, default 1:1.

Options:1:12:33:23:44:34:55:49:16

Show all (1)

16:9

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "fibo-gen-1.5/text-to-image",
  "input": {
    "seed": 5555,
    "prompt": "…",
    "aspect_ratio": "1:1"
  }
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "fibo-gen-1.5/text-to-image",
    input: {
      "seed": 5555,
      "prompt": "…",
      "aspect_ratio": "1:1"
    }
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "fibo-gen-1.5/text-to-image",
        "input": {
          "seed": 5555,
          "prompt": "…",
          "aspect_ratio": "1:1"
        }
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}