Sebastian Bald Image Generator

Discover the Sebastian Bald Image Generator, a powerful tool for Text-to-Image Generation and LoRA Fine-tuning. See what makes this AI model special!

Platform: Replicate

Text-to-ImageLoRA Fine-TuningImage Inpainting

20 runs

H100

License Check Required

🚀Function Overview

Generates and modifies images through text prompts with support for inpainting, LoRA fine-tuning, and extensive generation controls.

Key Features

Text-to-image generation with trigger word activation
Image inpainting using masks
Aspect ratio and custom resolution controls
Quality/speed trade-off via model selection
LoRA scaling and external LoRA integration
Output format and quality adjustments

Use Cases

•Creating character portraits from textual descriptions
•Editing images via inpainting masks
•Generating stylized visuals using LoRA weights
•Producing multiple image variations from prompts

⚙️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",
  "width": 1024,
  "height": 1024,
  "prompt": "masterpiece, best quality, ultra-detailed, photorealistic, 8k, cinematic lighting, hyperrealistic studio portrait of SEBBALD with extremely short hair (nearly bald), distinctive facial features captured accurately by LoRA, medium shot chest to head, arms crossed, looking directly into camera with friendly confident expression. Clothing: neutral dark blue round neck t-shirt, matte fabric texture.\nLighting: strong soft key light from above-left, moderate cool fill light from front-right, neon-lime rim light on right contour (Hex #CCFF00), electric-blue rim light on left contour (Hex #0DCAF0), optional subtle electric-blue fill from below-left.\nBackground: bright off-white (#F5F5F5) with very subtle isometric line/grid texture in faint light gray (near invisible), minimal radial halo effect: a very soft, almost imperceptible neon-lime or electric-blue edge around figure to separate from background. Soft vignette.\nSpecular highlights: natural skin highlights (forehead, cheeks, eyes), subtle fabric highlights on blazer, slight reflective accents of rim lights on shoulders and head.\nMood: premium, futuristic-charming, minimalistic but striking, friendly and confident.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "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/lvX8uFGu2ErpGBDfKWq4MxaIP6slEOUF0DxbsZeO4zhSZ61UA/out-0.webp

https://replicate.delivery/xezq/Kfchv5CwHIUfiUGfFcird1sofyFnudirHT7K8FasAjsKlpXTB/out-1.webp

https://replicate.delivery/xezq/hW2zOVgT7iYGPxAGe4csmh5GmAu354VGoyd6ENeMWOQSZ61UA/out-2.webp

https://replicate.delivery/xezq/xpQRVPfvqpXBSK68RUNQca57vRvpw4zTEzipVMHQUebSZ61UA/out-3.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 20
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Text-to-Image GenerationLoRA Fine-tuningImage InpaintingCustom ResolutionStylized VisualsCharacter PortraitsMultiple Image Variations

Related Models

Sasha Advertising Persona

Sasha is a young boy advertising persona

Blog Image Generator by Nat Wanderer

A model for generating and editing images using text prompts, with support for image-to-image transformations and inpainting.

Anomalapictures Fauna3

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