Lemuia AI Image Generator

Lemuia AI Image Generator empowers you to create stunning visuals from text prompts or existing images. See what makes this AI model special!

Platform: Replicate

Image GenerationImage InpaintingLoRA AdaptationImage-to-Image Translation

39 runs

H100

License Check Required

🚀Function Overview

Generates images from text prompts or existing images, supporting inpainting, style control via LoRA, and parameter adjustments for quality/speed trade-offs.

Key Features

Text-to-image generation with prompt-based control
Image-to-image transformation via input images and masks
Adjustable LoRA scales for style/concept customization
Model selection between 'dev' (quality) and 'schnell' (speed)
Configurable resolution, aspect ratio, and output formats
Parameter control: guidance scale, denoising steps, seed reproducibility

Use Cases

•Converting text descriptions into visual artwork
•Editing/enhancing existing images via inpainting
•Creating stylistic variations using LoRA adapters
•Rapid prototyping with fast generation mode

⚙️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_stps

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": "\"Lemu, a man with a perfectly shaved, smooth bald head that reflects a clean and polished look, is featured in a high-quality, casual yet formal portrait. He has a medium-length, well-groomed, and neatly trimmed black beard with sharp, delineated edges, paired with modern rectangular glasses. Lemu weighs around 100 kg and has a moderately muscular build, with a strong but not overly bulky physique. He is dressed in a stylish, tailored navy blue suit with a crisp white open-collared shirt, no tie, giving a relaxed yet professional vibe. He is sitting in a legal office, showing a warm, confident smile on his face, his body slightly turned to the side in a relaxed posture. The background features a sophisticated legal office setting with large floor-to-ceiling windows, soft natural light streaming in, a polished wooden desk with legal books and a gavel, and a leather chair. The overall atmosphere is polished and approachable, with a focus on sharp details in the navy blue suit, the perfectly shaved bald head, and a professional legal office environment.\"",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 2,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 2.54,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/iVVmggzP1houI5zgeZOF9SqfI5KihHXogXYLgfLPkY3rnJ5oA/out-0.webp

https://replicate.delivery/xezq/aPDdO4G1jW5ZLdLq2RJpeDRcnwRQB8EnUtGlsfEtyoE1zkcUA/out-1.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 39
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Text-to-Image GenerationImage InpaintingLoRA AdaptationImage-to-Image TransformationRapid PrototypingCustomizable ResolutionAdjustable Quality

Related Models

Sector Keypad 2 Image Generation

A model for generating and modifying images through text prompts, inpainting, and LoRA adaptations.

Mafuwoodstock Image Generation

A model for generating and editing images through text prompts, inpainting, and LoRA scaling.

BMMBJEZ AI Image Generation

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