Sasha Advertising Persona

Discover the Sasha Advertising Persona, your go-to AI for generating compelling advertising visuals and character portraits.

Platform: Replicate

Character GenerationText-to-ImageImage InpaintingLoRA Fine-Tuning

3 runs

H100

License Check Required

🚀Function Overview

A fine-tuned image generation model for creating stylized images of the character Sasha, supporting text-to-image, image-to-image transformations, and inpainting with flexible control parameters.

Key Features

Generates images from text prompts using diffusion
Image-to-image transformation with adjustable strength
Supports inpainting with custom masks
Aspect ratio and resolution customization
Multiple LoRA support for style control
Fast fp8-optimized generation mode
Adjustable denoising steps and guidance scale

Use Cases

•Advertising visuals featuring the Sasha character
•Character portrait generation
•Image editing and enhancement
•Concept art development

⚙️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": "sasha. a young boy. Close-up. Studio lighting. Having a cat. Looking at the camera. Smiling. ",
  "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/FmHHFfRsUA3NDisJSy9R3k3EtK5E9BZ6crMKRATiM2Kz6QaKA/out-0.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 3
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Advertising VisualsCharacter Portrait GenerationImage EditingConcept Art DevelopmentText-to-Image GenerationImage-to-Image TransformationImage InpaintingLoRA Fine-tuning

Related Models

Aron AI Image Generator

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

fgtensei Replicate

A model for generating and editing images using text prompts, image inputs, and inpainting capabilities with LoRA integration.

Rebel Image Generator

rebel generates images that feel like memories of an era long gone but ever present, etched in time.