HWD Image Generator

Discover the HWD Image Generator, a powerful tool for text-to-image creation and image inpainting. Let's explore what this AI model can do for you!

Platform: Replicate

Text-to-ImageImage InpaintingLoRA IntegrationParameter-Driven Generation

17 runs

H100

License Check Required

🚀Function Overview

Generates high-quality images from text prompts while supporting image-to-image transformations, inpainting with masks, and extensive customization through fine-grained parameters.

Key Features

Text-to-image generation with trigger word activation
Image inpainting using masks
Edge-to-edge custom aspect ratio and resolution controls
Style customization via LoRA weights
Adjustable denoising steps and guidance scale
FP8 quantized fast generation mode

Use Cases

•Creating custom artwork from text descriptions
•Removing objects from photos via inpainting
•Style transfer and image enhancement
•Generating image variations with parameter tuning
•Rapid prototyping for design concepts

⚙️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 confident HWD with short dark hair, a beard, and sunglasses, standing in an urban street holding a large cardboard sign above his head. He wears a fitted black T-shirt and jeans, looking assertive. The cardboard sign has bold, handwritten text: \"Using ChatGPT Alone is a Mistake!\". In the background, a stylish and attractive woman in casual summer clothing walks past, subtly catching attention. The city street has brick buildings, outdoor cafes, and pedestrians, creating a lively urban vibe. Natural lighting with soft shadows enhances realism.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 90,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/WxMcH5uFSzoLKByoQC3IJUryIYdtgbYL2DkNkWdqrIvzQwLF/out-0.png

https://replicate.delivery/xezq/rEz7BloI89qpGNSBl4wUFuhdkEqiMdDfoovycSxCV6eODBvUA/out-1.png

https://replicate.delivery/xezq/q6M0dLeHjelbgU4OrcEf52f7uRkIsNsLXclNmF2AAIg6ME8SB/out-2.png

https://replicate.delivery/xezq/bUHdiKdyg0J0BdWctpFfbCvN5Wqe9yD0TlwY2CHJTllODBvUA/out-3.png

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 17
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Text-to-ImageImage InpaintingLoRA CustomizationCustom ArtworkDesign PrototypingParameter-Driven GenerationStyle Transfer

Related Models

Helbert Costa Image Generation

A model for generating and modifying images using text prompts and LoRA weights.

Modelo Raphael V3

A model for generating and modifying images using textual prompts and input images, supporting inpainting and style activation via trigger words.

Mike AI Image Generator

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