Fulbert AI Image Generator

Discover Fulbert AI, a powerful image generator that transforms text into stunning visuals. Discover how this AI model can transform your workflow!

Platform: Replicate

Text-to-ImageImage InpaintingLoRA ModelsCustom Aspect Ratios

88 runs

H100

License Check Required

🚀Function Overview

Generates, modifies, and inpaints images using text prompts with adjustable parameters for resolution, style transfer via LoRA, and safety settings.

Key Features

Text-to-image generation from prompts
Image-to-image translation and inpainting with mask input
LoRA model integration for style/concept activation
Customizable aspect ratios and resolutions
Fast mode optimization (fp8 quantized)
Adjustable denoising steps and guidance scale
Safety checker for generated content

Use Cases

•Creating digital artwork from text descriptions
•Editing photos via inpainting
•Applying specialized styles (e.g., Pixar, specific artist styles via LoRA)
•Generating character portraits with precise attributes
•Commercial image creation for marketing/advertising

⚙️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": "A photo of fulbert , standing with arms crossed in a powerful pose, intense gaze directed at the camera, slight confident smile, eyes looking straight into the lens.\n--ar 3:4 -- raw style\n--Subject wearing a textured light grey three-piece suit with a subtle houndstooth pattern, a crisp white shirt with fine blue stripes, and a burgundy silk tie featuring a geometric diamond pattern.\n--Accessories: luxury silver watch with black dial and metal bracelet, white pocket square with a thin blue border in the chest pocket.\n--Environment: White House office in Washington.\n--Lighting: professional studio setup with main key light from the front-left, subtle fill light to eliminate harsh shadows, rim light to separate the subject from the background.\n--Camera angle: head and torso framing, eye-level perspective, centered composition.\n--Composition: perfectly centered subject, rule of thirds applied with eyes directly aligned with the lens, symmetrical balance, strong vertical presence.\n--Post-processing: high-definition commercial quality, slight color grading for a warm professional tone, enhanced contrast to emphasize fabric texture.\n--Details: focus on facial features and suit fabric texture, visible skin pores and textile detail.\n--Refinement: extra attention to facial definition and suit material; clear rendering of skin and clothing texture.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "4:3",
  "output_format": "jpg",
  "guidance_scale": 3,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/kwfyv7iWeFoT50zywUyTWaeQH4eHMwXfMj8V7HIy956ZD9amC/out-0.jpg

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 88
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Text-to-Image GenerationImage InpaintingLoRA Model IntegrationCustom Aspect RatiosDigital Artwork CreationPhoto EditingStyle Transfer

Related Models

Slingit1 AI Image Generator

A model for generating and editing images using prompts, inpainting, and LoRA parameter adjustments.

FlaskBottle AI Model

A model for generating and editing images through text prompts, input images, masks, and LoRA model integration.

Tobogganstyle Image Generation

A model for generating images in a specific artistic style, with options for inpainting and adjustments.