Naledirae AI Image Generation

Unleash your creativity with Naledirae, a fine-tuned SDXL model for AI image generation, inpainting, and sophisticated image editing.

Platform: Replicate

SDXL Fine-tuneImage InpaintingText-to-ImageImage Editing

46 runs

L40S

License Check Required

🚀Function Overview

An SDXL-based fine-tuned model supporting text-to-image generation, image-to-image transformations, and masked inpainting with adjustable parameters.

Key Features

Text-to-image generation via prompts
Image-to-image transformation (img2img)
Mask-based inpainting (preserve/alter image regions)
Adjustable denoising steps and guidance scale
Supports LoRA scaling for fine-tuned outputs
Watermarking toggle and safety checker control

Use Cases

•Generating artwork from textual descriptions
•Editing existing images by modifying masked regions
•Creating photo-realistic variations of input images
•Commercial and artistic visual content production

⚙️Input Parameters

prompt

string

Input prompt

negative_prompt

string

Input Negative Prompt

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_outputs

integer

Number of images to output.

scheduler

string

scheduler

num_inference_steps

integer

Number of denoising steps

guidance_scale

number

Scale for classifier-free guidance

prompt_strength

number

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

seed

integer

Random seed. Leave blank to randomize the seed

refine

string

Which refine style to use

high_noise_frac

number

For expert_ensemble_refiner, the fraction of noise to use

refine_steps

integer

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

lora_scale

number

LoRA additive scale. Only applicable on trained models.

disable_safety_checker

boolean

Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)

💡Usage Examples

Example 1

Input Parameters

{
  "width": 1024,
  "height": 1024,
  "prompt": "naledirae woman, with a strong natual build, short cropped hair shot in natural lighting by annie leibovitz on a dslr camera in the desert in Sedona Arizona wearing an upscale flowing white evening gown holding a white chanel 22 bag.  ",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

Output Results

https://replicate.delivery/xezq/ZinrxCfaocQye0PLcuyrJopVLLunmIg2leifK8V5pCtM063SB/out-0.png

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: L40S
Run Count: 46
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

AI Image GenerationImage InpaintingText-to-ImageImage EditingSDXL Fine-tuneVisual Content ProductionArtwork Creation

Related Models

Lucy357 BH Image Generation

A model for generating and editing images based on textual prompts and input images.

Cyalon Image Generation

A model for image generation and manipulation with support for text prompts, image inputs, inpainting, and LoRA adaptations.

Mindy Generator

A model for generating images using text prompts with support for image-to-image translation, inpainting, and LoRA integration.