MTWR64 Image Generation Model

Discover the power of MTWR64, an advanced image generation model. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

Diffusion ModelImage InpaintingLoRA IntegrationCreative Generation

695 runs

H100

License Check Required

🚀Function Overview

Generates or modifies images from text prompts, supporting inpainting, image-to-image translation, and custom LoRA weighting for specialized styles.

Key Features

Text-to-image generation with prompt triggering
Image inpainting using masks
Modifiable aspect ratios/custom resolutions
LoRA scaling for fine-tuning outputs
Dual model modes (quality-focused 'dev' vs speed-optimized 'schnell')
Safety checker toggle
FP8 quantization for faster generation

Use Cases

•Creating digital art from text descriptions
•Editing existing images via inpainting
•Applying custom artistic styles via LoRA weights
•Prototyping visual concepts
•Batch image generation with parameter tuning

⚙️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": "mtwr High resolution images The image portrays a girl in a seductive bunny costume. She appears to be a young adult with long, straight, dark hair and a pair of large, round ear-like accessories commonly associated with bunny ears. They are wearing silver-colored lacy lingerie, delicate white thigh-high stockings, and a sheer, white, strapless bra. The bra features unique keyhole-style detailing at the front.\nThe costume has a distinctive black bow tie worn over a white lacy corset with lace-trimmed openings at the collar and ends in straps that secure the bra. The ears are strapped to the head, with the bands extending behind the neck.\nShe lying on the bed in the seductive and inviting posture, 8k, no blurry",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/Z87wmKmknRaPMFbEPGUagCMUBbQluLieYnPNBVnxXaa0JxSKA/out-0.png

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 695
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Text-to-image generationImage inpaintingLoRA integrationCustom resolutionsCreative generationDigital art creationVisual concept prototyping

Related Models

Vladu Image Generation

A model for generating and editing images using prompts, input images, and masks.

JuliaV2 Image Generation

A model for generating and editing images from text prompts with support for inpainting, custom adjustments, and LoRA fine-tuning.

Livvy Image Generation

A model for generating and editing images through text prompts with LoRA integration.