aleksa-codes / flux-ghibsky-illustration

Flux LoRA, use 'GHIBSKY style' to trigger generation, creates serene and enchanting landscapes with vibrant, surreal skies and intricate, Ghibli-inspired elements reminiscent of the atmospheric beauty found in Makoto Shinkai's works

  • Public
  • 62.4K runs
  • H100
  • Weights

Run aleksa-codes/flux-ghibsky-illustration with an API

Input schema

maskuri

Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

seedinteger

Random seed. Set for reproducible generation

imageuri

Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

modelstring

Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.

Default
"dev"
widthinteger

Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation

Minimum
256
Maximum
1440
heightinteger

Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation

Minimum
256
Maximum
1440
promptstring

Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.

go_fastboolean

Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16

extra_lorastring

Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'

lora_scalenumber

Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Default
1
Minimum
-1
Maximum
3
megapixelsstring

Approximate number of megapixels for generated image

Default
"1"
num_outputsinteger

Number of outputs to generate

Default
1
Minimum
1
Maximum
4
aspect_ratiostring

Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode

Default
"1:1"
output_formatstring

Format of the output images

Default
"webp"
guidance_scalenumber

Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5

Default
3
Maximum
10
output_qualityinteger

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default
80
Maximum
100
prompt_strengthnumber

Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image

Default
0.8
Maximum
1
extra_lora_scalenumber

Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Default
1
Minimum
-1
Maximum
3
num_inference_stepsinteger

Number of denoising steps. More steps can give more detailed images, but take longer.

Default
28
Minimum
1
Maximum
50
disable_safety_checkerboolean

Disable safety checker for generated images.

Output schema

Type
uri[]