Familia Alves Image Generator

Discover the Familia Alves Image Generator, an innovative tool for advanced image generation and manipulation through text prompts.

Platform: Replicate

Image GenerationImage InpaintingLoRA Style TransferPortrait Creation

29 runs

H100

License Check Required

🚀Function Overview

Generates and modifies images based on text prompts and input images, featuring inpainting capabilities, adjustable styles via LoRA, and control over image properties like resolution and aspect ratio.

Key Features

Text-to-image generation
Image-to-image transformation
Mask-based inpainting
LoRA style and concept customization
Adjustable resolution and aspect ratios
Control over generation speed and quality

Use Cases

•Creating custom portraits from textual descriptions
•Editing existing photos through inpainting
•Applying artistic styles to images
•Generating themed family portraits
•Producing marketing visuals with brand-specific elements

⚙️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": "ALVES[Positioned in a classic vertical composition: father standing next to mother, with a protective posture and serene expression; mother sitting partially to the side with her son on her lap, all looking at the camera lightly and firmly] [Light beige studio background, neutral and modern, without additional visual elements] [Right angle, medium shot with proportional framing of the three bodies and focus on the faces and gestures of proximity] [Editorial family portrait with elegant posture, sober and natural aesthetics] [Father wearing a light beige textured sweater and khaki pants; mother wearing a structured white shirt with puffed sleeves and light pants; son wearing a white shirt and grayish olive green pants, sitting relaxed] [Cotton and linen textures in light and neutral fabrics; [softly lit skin, natural hair and discreet accessories such as a metallic watch and small earrings] [Diffuse and uniform studio lighting that enhances volume, softens shadows and highlights expressions] [Palette of white, beige, khaki and light olive, with a warm monochromatic background] [Contemporary family portrait style with an editorial, minimalist and affectionate feel] [No external elements, no chromatic exaggerations, no color distortion] [Canon EOS R6 with RF 50mm f/1.2L lens, soft front lighting with side reflector] no estilo de ALVES",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "3:4",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/SJ6UQLyClUplENZoaSM38VW9aje5LGGKUEg1xpL7SB8EeqsUA/out-0.png

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 29
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Image GenerationImage InpaintingLoRA Style TransferPortrait CreationText-to-ImageImage-to-ImageCustom Portraits

Related Models

Mindy Generator

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

Sector SmokeBox

A model for generating and editing images from text prompts, supporting inpainting, image translation, and LoRA-based style adjustments.

Prashant Flux LORA

A model for generating images using the Flux framework with LoRA adaptations.