kadusantos Diffusion Model

Unleash your creativity with kadusantos, an advanced diffusion model for image generation and editing. See what makes this AI model special!

Platform: Replicate

Text-to-Image GenerationImage InpaintingLoRA Diffusion

16 runs

H100

License Check Required

🚀Function Overview

A diffusion model that generates images from text prompts, supports image-to-image translation, inpainting with masks, and LoRA customization for specialized styles or concepts.

Key Features

Generates images from text prompts using trigger words
Image-to-image transformation with adjustable strength
Mask-based inpainting functionality
Support for aspect ratios and custom dimensions
LoRA integration for style/concept tuning
Quantized model option for faster inference

Use Cases

•Creating character portraits with specific styles
•Editing images through inpainting
•Generating variations of existing images
•Applying custom art styles via LoRA models
•Producing marketing visuals from text descriptions

⚙️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": "kadusantos A man standing confidently in a green tailored suit with a black T-shirt underneath, in a dark, moody environment, front-facing with a strong yet calm expression. Shot from a low angle to enhance presence and stature. Hyper-realistic style, with detailed fabric texture and sharp facial features. Soft, diffused spotlight illuminates his face and upper body, casting deep shadows around. Background fades into darkness with subtle industrial elements barely visible. Muted green and black tones dominate. Inspired by neo-noir cinematography. --no blur, no distortion, no artifacts --camera: Sony A7R V --lens: 85mm f/1.4 GM",
  "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/Hj4fPDGu8FSOPKMSL9EMdAWNgJ4spI1jLtOHffk8LzfYuRISB/out-0.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 16
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Text-to-Image GenerationImage InpaintingLoRA CustomizationImage-to-Image TransformationCharacter PortraitsMarketing VisualsAspect Ratio ControlCustom Dimensions

Related Models

Anomalapictures Fauna3

A model for generating and editing images of fauna using text prompts, inpainting, and LoRA integrations.

Aron AI Image Generator

A model for generating and editing images using text prompts and input images, supporting inpainting and LoRA customization.

GetGems Chat Image Generator

A model for generating and editing images through text prompts, style adjustments, and inpainting capabilities.