MRGG-05-2025 Image Generation

Discover MRGG-05-2025, a versatile image generation model. Utilize text-to-image, inpainting, and LoRA customization. Try it now and see the results!

Platform: Replicate

Image DiffusionText-to-ImageInpaintingLoRA Customization

51 runs

H100

License Check Required

🚀Function Overview

A diffusion model that generates and modifies images using text prompts, input images, masks, and LoRA weights for customization.

Key Features

Text-to-image generation with prompt-based control
Image-to-image transformation and inpainting using masks
Adjustable aspect ratio, dimensions, and megapixels for output
Support for multiple inference models (dev for quality, schnell for speed)
LoRA weight integration for style or concept activation
Fine-tuning via denoising steps, guidance scale, and prompt strength

Use Cases

•Creating artwork from textual descriptions
•Editing existing images by replacing masked areas
•Generating prototypes or variations of visual content
•Customizing outputs using trained LoRA weights and triggers
•Batch image generation with quality vs speed options

⚙️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 stunning, hyper-realistic upper-body photo of MrGG, a vibrant and confident 30-year-young man, standing behind a sleek modern podium during a high-energy tech talk on Agentic AI. MrGG exudes sharp intelligence and effortless charisma. His physique appears trim and athletic, captured in a flattering angle that highlights his sharp jawline, well-defined features, and clear, energized eyes. He wears a stylish, smart-casual outfit — a slim-fit dark t-shirt paired with a lightweight bomber jacket or modern tech hoodie in charcoal or navy tones, giving off an effortlessly cool, Silicon Valley innovator vibe.\n\nHe is mid-speech, gesturing naturally with one hand while maintaining steady, magnetic eye contact with the audience (or the camera), giving the sense that he owns the room. A subtle, confident smile plays on his face — not too posed, just right.\n\nBehind him, a large futuristic digital screen displays the bold phrase \"FUTURE WITH AI\" in glowing, modern white sans-serif font. The backdrop features elegant, high-tech abstract visuals — softly glowing network lines, AI data flows, or a subtle matrix of nodes and circuits, adding sophistication and a sense of momentum to the scene.\n\nThe lighting is cinematic and flattering — soft key light on his face, with smooth diffusion that minimizes shadows and defines his features beautifully. The background is slightly blurred to keep the focus on MrGG, who appears poised, visionary, and magnetic — the kind of leader people instantly respect and want to listen to.\n\nThe whole composition is visually balanced, dynamic, and inspiring — capturing not just a speaker, but a powerful presence shaping the narrative of tomorrow’s AI-driven world.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/j1kksuXOWi5FN1fe4rfuz7dZwmuStxdoVqR2IYBufGPlIB8SB/out-0.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 51
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Image DiffusionText-to-ImageInpaintingLoRA CustomizationImage-to-Image TransformationCustomizable OutputBatch Generation

Related Models

Pupa Beta Image Generator

A model for generating and editing images through text prompts with inpainting capabilities and LoRA adjustments.

Flash-Beta.6 Image Generation

A model for generating and editing images with advanced controls like inpainting, style adaptation, and LoRA-based customizations.

Sector Savebox AI Image Generator

A model for generating and editing images with various settings and LoRA support.