G
GetLLMs

Luma Portrait

Unleash your creativity with Luma Portrait, the diffusion model for stylized portrait images. Discover how this AI model can transform your workflow!

Platform: Replicate
Portrait GenerationImage EnhancementLoRA Integration
50 runs
H100
License Check Required

🚀Function Overview

A diffusion model specialized in creating stylized portrait images with customizable parameters, supporting both text-to-image generation and image-to-image transformations like inpainting.

Key Features

  • Prompt-based image generation with trigger word activation
  • Image-to-image and inpainting capabilities
  • Custom aspect ratios and image dimensions
  • Adjustable LoRA scaling for style/concept control
  • Multiple output formats and quality settings
  • Speed optimization (FP8 quantized) vs precision (BF16) modes

Use Cases

  • Creating artistic portrait photography
  • Enhancing existing images with specific styles
  • Generating marketing visuals with branded aesthetics
  • Developing character designs for media productions

⚙️Input Parameters

prompt

string

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.

image

string

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

mask

string

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

aspect_ratio

string

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

height

integer

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

width

integer

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

prompt_strength

number

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

model

string

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

num_outputs

integer

Number of outputs to generate

num_inference_steps

integer

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

guidance_scale

number

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

seed

integer

Random seed. Set for reproducible generation

output_format

string

Format of the output images

output_quality

integer

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

disable_safety_checker

boolean

Disable safety checker for generated images.

go_fast

boolean

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

megapixels

string

Approximate number of megapixels for generated image

lora_scale

number

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.

extra_lora

string

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'

extra_lora_scale

number

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.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "dev",
  "prompt": "a young girl with her dog bright and vibrant lighting, glowing skin, pastel pink and blue tones in the background, cinematic shallow depth of field, shot on a Canon RF 85mm f/1.2, soft bokeh, fashion editorial styling, sharp facial detail, sparkling highlights, natural pose with the style of LUMPOR, holding cotton candy, wearing glitter makeup, backlit with fairy lights",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/BnWUZIs6fYwDUiNwwLDNdsIeOlHfw4PIo5egOVD07gLYYxoSB/out-0.webp

Quick Actions

Technical Specifications

Hardware Type
H100
Run Count
50
Commercial Use
Unknown/Restricted
Platform
Replicate

Related Keywords

Artistic Portrait PhotographyImage EnhancementStylized Portrait ImagesText-to-Image GenerationImage-to-Image TransformationLoRA IntegrationCustom Aspect RatiosCharacter Design