Bruna Depaula Image Generator

Discover Bruna Depaula, an advanced image generator capable of creating and editing images with remarkable precision. Try it now and see the results!

Platform: Replicate

Image InpaintingLoRA Fine-tuningPortrait GenerationImage-to-Image Synthesis

41 runs

H100

License Check Required

🚀Function Overview

Generates, modifies, or inpaints images using text prompts, input images, and masks with LoRA adjustments for personalized outputs.

Key Features

Text-to-image generation from prompts
Image-to-image translation and inpainting capabilities
LoRA fine-tuning integration for style/object customization
Fast generation mode with optimized inference
Adjustable resolution, aspect ratio, and quality parameters

Use Cases

•Creating studio-quality portraits from prompts
•Editing existing images through inpainting
•Generating custom objects/styles via LoRA
•Batch image generation with parameter tuning

⚙️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

{
  "mask": "https://replicate.delivery/pbxt/MlwegYrc9RFuQrReZTwkYnoT9dkVt1ATEqxs2XHk2cSSsg46/ana_site-1.jpg",
  "model": "dev",
  "prompt": "brunadepaula Ultra-realistic, high-quality studio portrait, wearing a black turtleneck sweater. She has a confident and charismatic expression that conveys intelligence and approachability. Her eyes are well-lit, creating an engaging and expressive gaze.\n\nShe is leaning gently against a wall, with a relaxed yet professional posture, exuding confidence and authority without stiffness. Her stance is slightly angled, adding dynamism and authenticity to the composition.\n\nThe photograph is taken in a professional studio, using a Canon EOS R5 + RF 85mm f/1.2L lens, ensuring a shallow depth of field for a softly blurred background. The setting is minimalist, featuring a neutral gray wall backdrop, creating a sophisticated and timeless aesthetic.\n\nThe lighting mimics a stage or keynote presentation, with a soft spotlight from above, enhancing her features in a dramatic yet elegant way. A subtle rim light is used to separate her from the background, adding depth. The final image has a cinematic, high-end editorial quality, reminiscent of visionary CEO and leadership portraits.",
  "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/jfmfNfFDnaOFoJV3eDSD0PfRLL68RSAxEMCa8tVvfafuoYhPKA/out-0.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 41
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Image GenerationLoRA Fine-tuningImage InpaintingImage-to-ImagePortrait GenerationText-to-ImageFast Generation

Related Models

Mindy Generator

A model for generating images using text prompts with support for image-to-image translation, inpainting, and LoRA integration.

Judith AI Image Generator

Un modèle qui génere des image qui ressemble à judith

Familia Alves Image Generator

A model for generating and editing images using text prompts and input images with support for inpainting and style adjustments through LoRA.