Good SDXL Models Plus LoRAs

Unleash your creativity with Good SDXL Models Plus LoRAs. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

Stable Diffusion XLLoRA AdaptersImage InpaintingText-to-Image

188 runs

L40S

License Check Required

🚀Function Overview

Generates and edits images using SDXL models and LoRA adapters for text-to-image, image-to-image, and inpainting tasks.

Key Features

Multiple SDXL model options (e.g., RealVisXL, CyberRealistic)
Fine-tuning via LoRA adapter weights
Resolution control (128-2048 pixels)
Sampling method selection
Denoising step adjustment
Prompt weighting and negative prompting

Use Cases

•Creating artwork from text descriptions
•Modifying existing images through inpainting
•Style transfer using LoRA adapters
•Generating high-resolution digital art

⚙️Input Parameters

prompt

string

Input prompt

negative_prompt

string

Specify things to not see in the output

image

string

Input image for img2img or inpaint mode

mask

string

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted

width

integer

Width of output image

height

integer

Height of output image

num_inference_steps

integer

Number of denoising steps

guidance_scale

number

Scale for classifier-free guidance

prompt_strength

number

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

model_name

string

Choose which model to use

lora_selection

string

Select a LoRA or LoRA combination to apply

lora_weight

number

LoRA weight (higher values increase effect strength)

sampler

string

Choose a sampler

scheduler_type

string

Choose a scheduler type

seed

integer

Random seed. Leave blank to randomize the seed

💡Usage Examples

Example 1

Input Parameters

{
  "width": 1024,
  "height": 1024,
  "prompt": "magical Castel",
  "sampler": "DPMPP_2M",
  "model_name": "cyberrealistic_xl_cyberdelia",
  "lora_weight": 0.8,
  "guidance_scale": 7.5,
  "lora_selection": "none",
  "scheduler_type": "karras",
  "negative_prompt": "worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art, mutated, deformed, distorted, disfigured, body horror, watermark, text, meme, bad proportions, cropped head, out of frame, cut off, ugly, duplicate, mutilated, mutation, disgusting, bad anatomy, bad hands, three hands, three legs, bad feet, three feet",
  "prompt_strength": 0.8,
  "num_inference_steps": 30
}

Output Results

https://replicate.delivery/xezq/huXeGcwUpmzvb6JfOHiBrA33vYjeC13EXuVD6rTvss6cYC3oA/output.png

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: L40S
Run Count: 188
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Stable Diffusion XLLoRA AdaptersImage InpaintingText-to-ImageImage EditingStyle TransferHigh-Resolution Digital Art

Related Models

Pitiduval

A model for generating and editing images using text prompts and input images.

Modelo Raphael V3

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

Helbert Costa Image Generation

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