FLUX 3 Image
Black Forest Labs' FLUX 3 image model. Text to image, and editing or combining up to ten reference images.
- Model id:
bfl/flux-3-image - Type: Image, from Black Forest Labs
- Modes: Text to image, Image edit
- Prompt: up to 4,000 characters
- Canceling: Only while queued. Generations finish within seconds once submitted.
Parameters
Set these in params. Anything left out takes the default, which is what the price estimate assumes.
| Parameter | Accepted values | Default |
|---|---|---|
resolution | 1k, 1.5k, 2k, 4k | 1k |
aspect_ratio | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 4:5, 5:4, 21:9, 9:21, 2:1, 1:2, 7:5, 5:7 | 1:1 |
num_outputs | 1 only | 1 |
output_format | png, jpeg, webp | provider's |
References
Pass media in references, each with a role and an upload_id or HTTPS url (Uploads). When mode is left out it is inferred from the roles.
| Role | Used as | At most |
|---|---|---|
source_image | Image to edit | 1 |
reference_image | Subject or style reference | 9 |
Pricing
Billed per image delivered, varying by resolution. The full price list for your account is on the dashboard's billing page and in pricing from GET /v1/models/bfl%2Fflux-3-image. Each request reserves its maximum price and is charged for what was produced (Pricing and credits).
Examples
Square image
import { RawFrame } from "@rawframe/sdk";
const rf = new RawFrame();
const generation = await rf.generations.createAndWait({
model: "bfl/flux-3-image",
prompt: "A ceramic teapot shaped like a fox, soft studio light, product photo",
params: { aspect_ratio: "1:1" },
});
console.log(generation.outputs?.[0]?.url);Wide image
import { RawFrame } from "@rawframe/sdk";
const rf = new RawFrame();
const generation = await rf.generations.createAndWait({
model: "bfl/flux-3-image",
prompt: "A lighthouse on a basalt cliff at dusk, long exposure waves",
params: { aspect_ratio: "16:9" },
});
console.log(generation.outputs?.[0]?.url);Wan 3.0
Alibaba's Wan 3.0 video model (preview). Text to video, image to video from a first and optional last frame, and video guided by up to ten reference images, 2 to 30 seconds with optional audio.
FLUX 3 Video
Black Forest Labs' FLUX 3 video model. Text to video and image to video from a first and optional last frame, up to 20 seconds and 4K, with optional generated audio.