Aderonke LoRA

Discover Aderonke LoRA, a powerful model for image generation and modification. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

Image GenerationLoRA AdaptationImage InpaintingDiffusion Models

84 runs

H100

License Check Required

🚀Function Overview

Generates and modifies images through text prompts, supporting custom aspect ratios, inpainting, image-to-image transformations, and LoRA weight integration for specialized outputs.

Key Features

Text-to-image generation using diffusion models
Image inpainting and image-to-image transformation capabilities
Supports custom aspect ratios and resolutions
Optimized speed modes with quantized fp8 models
LoRA weight scaling for targeted style/object activation
Adjustable denoising steps and prompt strength parameters

Use Cases

•Creating custom character illustrations
•Modifying existing images via inpainting
•Generating promotional visuals from text descriptions
•Style transfer using specialized LoRA weights

⚙️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": "ADERONKE sits poised in a soft-lit, elegant home office, facing the camera with a confident, welcoming presence. She wears a tailored emerald green dress — modest, structured, and graceful — which complements her rich brown complexion. Her locs are neatly styled and pulled away from her face, allowing her clear-lens glasses and gold drop earrings to frame her expression. Her makeup is polished yet natural, with a soft glow highlighting her cheeks.\n\nShe’s seated in a contemporary fabric chair, hands gently resting apart on her lap or on the armrests — not crossed — reflecting openness and ease. Behind her, two large framed prints hang on the warm beige wall. The left frame reads: “Your Voice is Your Power,” and the right one simply states: “Build Boldly.”\n\nThe background feels inviting and meaningful — a tall indoor plant adds lush greenery, a shelf displays a few neatly stacked leadership books and personal items, and soft lighting warms the wooden floors. The atmosphere is professional but personal, reflecting a space built with intention.\n\nADERONKE speaks into a discreet lapel mic clipped near her neckline, mid-session in a recorded message or virtual class. A subtle overlay in the lower third of the image reads: “www.belgabt.com – Digital Business Coaching with Aderonke.”\n\nArt Style: Cinematic photorealism\nPose & Framing: Mid-shot, eye-level, arms relaxed, no hand-folding\nMood: Empowering, confident, open\nLighting: A blend of natural daylight and diffused artificial light for clarity and warmth\nSetting: Tastefully styled home office with motivational accents and personal character\n\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "16:9",
  "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/Qwru9OEEWOZoFJIPsfWLDWNMYk4VGczXTHg3tZ9aDGSsHCTKA/out-0.png

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 84
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Image GenerationLoRA Weight IntegrationImage InpaintingText-to-ImageCustom Aspect RatiosStyle TransferPromotional Visuals

Related Models

Mike AI Image Generator

A model for generating and modifying images using text prompts, input images, masks, and LoRA-based style adjustments.

Avatar Image Generation

A model for generating images including avatars through text prompts and image inputs with LoRA scaling and aspect ratio controls.

Pitiduval

A model for generating and editing images using text prompts and input images.