Back to Toolbox
Endpoint
https://fal.run/fal-ai/flux-krea-lora
Model ID
fal-ai/flux-krea-lora
Category
Text-to-image · inference
Tags
FLUX.1 Krea [dev] with LoRAs
Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.
LoRA
Personalization
Styles
Brand
Status
Idle
Response
Waiting for first request...
Generated Images
Input Schema
prompt (string, required)
The text prompt that drives generation.
image_size (enum | object)
Preset ratio token such as landscape_4_3 or a custom { width, height } object.
num_inference_steps (integer)
Number of diffusion steps. Default 28, max 50.
seed (integer)
Lock a generation so repeated calls return the same output.
loras (list<LoraWeight>)
Each entry accepts a path/URL plus a scale. They merge before sampling.
guidance_scale (float)
Classifier-free guidance strength. Default 3.5 (0-35).
sync_mode (boolean)
Wait for the render and asset upload before returning.
num_images (integer)
Images per request. Default 1 for streaming. Range 1-4.
enable_safety_checker (boolean)
Enable fal.ai safety guardrails. Default true.
output_format (enum)
jpeg or png. Default jpeg.
Output Schema
images
Array of objects with url and content_type.
timings
Latency breakdown for queue, generation, and upload.
seed
The seed used for the render (echoed back).
has_nsfw_concepts
Boolean flags describing safety findings.
prompt
The prompt that produced the response (echoed back).
Usage Examples
cURL
curl --request POST \
--url https://fal.run/fal-ai/flux-krea-lora \
--header "Authorization: Key $FAL_KEY" \
--header "Content-Type: application/json" \
--data '{
"prompt": "Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word \"FLUX\" is painted over it in big, white brush strokes with visible texture."
}'
Python
import fal_client
def on_queue_update(update):
if isinstance(update, fal_client.InProgress):
for log in update.logs:
print(log["message"])
result = fal_client.subscribe(
"fal-ai/flux-krea-lora",
arguments={
"prompt": "Extreme close-up of a single tiger eye..."
},
with_logs=True,
on_queue_update=on_queue_update,
)
print(result)
JavaScript
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("fal-ai/flux-krea-lora", {
input: {
prompt: "Extreme close-up of a single tiger eye..."
},
logs: true,
onQueueUpdate: (update) => {
if (update.status === "IN_PROGRESS") {
update.logs.map((log) => log.message).forEach(console.log);
}
},
});
console.log(result.data);
console.log(result.requestId);