Flux 3 Image
Neural Network
Flux 3 Image model by Black Forest Labs: generate and edit images using text descriptions and references.
Specifications
- Input
- text, images
- Output
- images
- Resolution
- 768sq, 1k, 1.5k, 2k, 4k
- Aspect ratio
- auto, 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21
- File formats
- WEBP, JPG, PNG
import OpenAI from 'openai';
const openai = new OpenAI({
apiKey: '<your bothub access token>',
baseURL: 'https://openai.bothub.chat/v1'
});
async function main() {
const response = await openai.images.generate({
model: 'flux-3-image',
prompt: 'a white siamese cat',
n: 1,
size: '1024x1024'
});
const imageUrl = response.data[0].url;
}
main();
How it works Flux 3 Image?
Flux 3 Image is Black Forest Labs' flagship model for image generation and editing. It accepts a text description and up to ten input images simultaneously, allowing you to assemble complex scenes from multiple references. Generation occurs in fixed resolutions, while editing relies on source images combined with descriptions. Through BotHub, the model opens in the same window as other generators: access without VPN or foreign cards, pay with Russian cards as you go, and purchased tokens do not expire. The multi-model API with an OpenAI-compatible interface allows you to integrate Flux 3 Image into your product and switch to another model later without rewriting the integration, while data is transmitted via AES-GCM encryption and is not saved. Designers create visual series for brands based on references, marketers prepare banners and campaign creatives, content creators make covers and illustrations for articles, and developers embed generation into applications and internal services. For companies: contracts, invoices, electronic document management, and an admin panel with limits.Frequently asked questions about Flux 3 Image
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
This is an image generation model: it creates images from text descriptions and also works in image-to-image mode. It is suitable for concepts, illustrations, visuals for social media and advertising, covers, variations, and refining existing shots based on references.
You get a raster image ready for download and further processing. Specific resolution presets and aspect ratios depend on request parameters, so it is easiest to set the desired format in the BotHub interface and compare several generation options.
Our data does not indicate a step-by-step reasoning mode for this model: it is focused on visual generation, not text-based chains of thought. If you need a detailed analysis of a task, use a text model with reasoning in the same BotHub window.
Our data does not indicate support for function calling or structured output for this model. However, it is accessed via the unified OpenAI-compatible BotHub API, so you can embed image generation into your service or pipeline without a separate integration.
You can upload images: the model supports image-to-image mode, meaning it takes your frame as a reference and builds a new result based on it. Audio and video inputs are not indicated in our data; for such tasks, select a specialized model from the catalog.
We do not publish statements about prompt languages for this model, so test it with your task: write the description as you prefer and compare the result with a more detailed version. The BotHub interface, support, and payment with Russian cards are available to you without a VPN.