Create Predictions - General - API Doc-CometAPI

Overview

The Replicate Predictions API provides the ability to generate high-quality images using various FLUX models from Black Forest Labs through the standard Replicate format. The API supports a comprehensive range of FLUX model variants, each optimized for different use cases, from rapid prototyping to professional-grade image generation. Users can seamlessly switch between different models by simply changing the model name in the URL path, making it flexible for various creative and commercial applications. The API offers extensive customization options including aspect ratio control, output format selection, quality settings, and advanced generation parameters to fine-tune the image creation process.

Due to significant differences in parameter lists across models, please refer to the Replicate official documentation for more information.

⚠️ Parameter Format Note: We are compatible with Replicate's parameter format, but all parameters must be placed within the input object. For specific parameters supported by each model, please refer to the corresponding official model page (e.g., flux-2-pro).

Example:

{
  "input": {
    "prompt": "your prompt here",
    "resolution": "1 MP",
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "output_quality": 80,
    "safety_tolerance": 2
  }
}

If you want to retrieve the generated results later, you can use the id returned by this API through the query endpoint to get the relevant content.

Supported Models

black-forest-labs/flux-2-pro

black-forest-labs/flux-2-dev

black-forest-labs/flux-2-flex

black-forest-labs/flux-kontext-max

black-forest-labs/flux-kontext-pro

black-forest-labs/flux-schnell

black-forest-labs/flux-pro

black-forest-labs/flux-dev

black-forest-labs/flux-1.1-pro-ultra

black-forest-labs/flux-1.1-pro

FAQ

⚠️ Image Reference Support

Issue: Not all FLUX models support image reference functionality

Solution: Only the flux-kontext model series (flux-kontext-max and flux-kontext-pro) supports the input_image parameter for referencing existing images. Other FLUX models do not support this feature and can only generate images based on text prompts.

curl --location --request POST 'https://api.cometapi.com/replicate/v1/models/black-forest-labs/flux-pro/predictions' \ --header 'Authorization: Bearer ' \ --header 'Content-Type: application/json' \ --data-raw '{ "input": { "prompt": "Merge images and return the main subject within the image.", "input_images": [ "https://replicate.delivery/xezq/Q9jOVfT4nmT6YaUGe7fwMe85kYPNziFq18j850Sg6YvPlk0WB/tmpzq6ncmxa.jpg", "https://h2.inkwai.com/bs2/upload-ylab-stunt/se/ai_portal_queue_mmu_image_upscale_aiweb/3214b798-e1b4-4b00-b7af-72b5b0417420_raw_image_0.jpg" ], "output_format": "jpg", "aspect_ratio": "16:9" } }'

{ "id": "k31cbm70fdrm80ctg73s0zcwgc", "model": "black-forest-labs/flux-kontext-max", "version": "hidden", "input": { "aspect_ratio": "16:9", "input_image": "https://h2.inkwai.com/bs2/upload-ylab-stunt/se/ai_portal_queue_mmu_image_upscale_aiweb/3214b798-e1b4-4b00-b7af-72b5b0417420_raw_image_0.jpg", "input_image_2": "https://replicate.delivery/xezq/XfwWjHJ7HfrmXE6ukuLVEpXWfeQ3PQeRI5mApuLXRxST7XMmC/tmpc91tlq20.png", "input_image_3": "https://filesystem.site/cdn/20250414/chxiLc2O45zoLT8BCrQ6WQlTvGDDnK.png", "input_image_4": "https://filesystem.site/cdn/20250414/chxiLc2O45zoLT8BCrQ6WQlTvGDDnK.png", "output_format": "jpg", "prompt": "black forest gateau cake spelling out the words \"FLUX SCHNELL\", tasty, food photography, dynamic shot" }, "logs": "", "output": null, "data_removed": false, "error": null, "source": "api", "status": "starting", "created_at": "2025-11-14T09:52:31.355Z", "urls": { "cancel": "https://api.replicate.com/v1/predictions/k31cbm70fdrm80ctg73s0zcwgc/cancel", "get": "https://api.replicate.com/v1/predictions/k31cbm70fdrm80ctg73s0zcwgc", "stream": "https://stream.replicate.com/v1/files/bcwr-xbztqryuzofyta6vb5yrmcarksz7rsfopeykdcloxinsrjqad5aq", "web": "https://replicate.com/p/k31cbm70fdrm80ctg73s0zcwgc" } }

Create Predictions - General

Overview

Supported Models

FAQ

⚠️ Image Reference Support

Request

Responses

Create Predictions - General

Overview#

Supported Models#

FAQ#

⚠️ Image Reference Support#

Request

Responses

Overview

Supported Models

FAQ

⚠️ Image Reference Support