Chewy Lora Image Generation

Discover the power of Chewy Lora for advanced image generation and creative control. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

LoRA Image GenerationImage InpaintingCustom Art Creation

20 runs

H100

License Check Required

🚀Function Overview

Generates customized images from prompts and inputs, supporting inpainting, image-to-image transformations, and LoRA-based style/concept adaptation

Key Features

Text-to-image generation with trigger words
Image inpainting using masks
Adjustable LoRA scales for fine control
Multiple resolution/aspect ratio options
Faster generation with optimized quantization mode
Safety checker for content moderation

Use Cases

•Generating artwork from text descriptions
•Editing existing images through masked inpainting
•Applying specific artistic styles using LoRA weights
•Creating character designs or concept art

⚙️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

{
  "image": "https://replicate.delivery/pbxt/N5anS47yg1gq5Wg8nqR0lEuZRRa66mIuW4oDea4FOAOFvbfm/IMG_4082.jpeg",
  "model": "dev",
  "prompt": "Tok as a massive brute sitting behind a work desk in an office. His arm are muscular and beefy. Bulging out of hit short sleeve polo. His chest and belly spilling over the desk and he is way too big for the desk. His belly and shirt digging into the desk that is in front of him. Make his arms muscular and huge and beefy and strong and bulging out and stretching the fabric of his sleeves on his shirt. ",
  "go_fast": false,
  "lora_scale": 0.85,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.91,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/Y27mhf32krT0XyOWhdOXWty8laBd6bPKdne7xbNuESKJiSxUA/out-0.webp

Quick Actions

Use NowView Documentation

Technical Specifications

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

Related Keywords

Image CustomizationLoRA AdaptersImage InpaintingText-to-image GenerationArtistic StylesConcept ArtCharacter Design

Related Models

Hair by 123christianpoop

A model for generating and editing images with a focus on hairstyles using diffusion techniques and LoRA customization.

Franface1 Image Generation

A model for generating and editing images using text prompts and input images with LoRA style transfer capabilities.

jdreetz Fans Toys Generator

A model for generating and editing fan art and toy-like character images using text prompts and reference images.