Genpack AI Image Generator

Genpack AI Image Generator is a powerful tool for generating and editing images. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

Image GenerationInpaintingLoRA AdaptationProduct Packaging Design

23 runs

H100

License Check Required

🚀Function Overview

Generates and manipulates images based on text prompts with options for custom aspect ratios, seed control, and LoRA-based style adjustments.

Key Features

Text-to-image generation with prompt triggers
Inpainting capabilities using image masks
Support for multiple LoRA adapters
Custom dimension control and aspect ratio presets
Fast generation mode with FP8 quantization

Use Cases

•Product packaging design
•Concept art generation
•Image editing and enhancement
•Style transfer via LoRA weights
•Prototyping visual assets

⚙️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": "packaging pf PGKTH The image features a dietary supplement product named \"Pilonix\" The packaging includes a blue and white box alongside a dark brown bottle with a black cap. Both the box and bottle have a similar design, displaying the product name \"Pilonix\" in bold blue letters. Below the name, the label states \"Dietary Supplement Product\" in English and “ ผลิตภัณฑ์เสริมอาหาร“ in Thai.\nThe key ingredients mentioned on the packaging are \"Rutin Extract\" and \"Curcumin Extract.\" The lower section of both the box and bottle label contains icons and text indicating that the product contains 20 capsules. The design uses blue and green gradient accents, giving a clean and modern appearance.\nThe product appears to be positioned for health-conscious consumers, likely promoting Hemorrhoids support due to the presence of Rutin and Curcumin extract.\nThe overall design is clean and professional, with a focus on natural healing and digestive health.\n\n",
  "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/nyGpebLUR31bBCBm4F9PbjIX03ic4ZzllkLx9LHmqE5QXUPKA/out-0.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 23
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Image GenerationInpaintingLoRA AdaptationsProduct Packaging DesignConcept Art GenerationImage EditingStyle Transfer

Related Models

Flash-Beta.6 Image Generation

A model for generating and editing images with advanced controls like inpainting, style adaptation, and LoRA-based customizations.

Alex2 Image Generation AI

A model for generating and editing images using text prompts with inpainting and LoRA customization capabilities.

pr1modelface

A model for generating and editing images using text prompts and input images, supporting inpainting and style transfer via LoRA integration.