Klemdepo Image Generator

Discover the Klemdepo Image Generator, a powerful tool for text-to-image and image-to-image generation. See what makes this AI model special!

Platform: Replicate

Image GenerationImage InpaintingLoRA IntegrationAspect Ratio Control

15 runs

H100

License Check Required

🚀Function Overview

Generates and edits images based on text prompts, input images, and masks while offering extensive controls for resolution, style, speed, and model selection.

Key Features

Text-to-image generation via prompts
Image-to-image translation capabilities
Mask-based inpainting functionality
Custom aspect ratio and resolution settings
LoRA (Low-Rank Adaptation) support for style customization
Multiple model variants (dev/schnell) for quality/speed trade-offs
Adjustable denoising steps and guidance scale

Use Cases

•Furniture visualization (e.g., showcasing products in environments)
•Creative content generation for marketing
•Photorealistic image editing and enhancement
•Artistic style transfer using LoRA models

⚙️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": "Scandinavian-inspired boho living room with soft natural light and minimalist styling, shot from a frontal camera angle at slightly below eye-level. The focal point is a KLEMDEPO2 sofa in the center, with light beige upholstery, straight edges, slim wooden legs, and a clean contemporary silhouette. The KLEMDEPO2 sofa is styled with textured throw pillows in ivory, taupe, and beige tones, along with a knitted blanket draped casually on one arm. Behind the sofa, the wall is painted soft off-white, decorated with floating wooden shelves and framed abstract line art in a warm neutral palette.\n\nTo the left and right of the KLEMDEPO2 sofa, wooden side tables and open shelving units hold ceramic vases, potted greenery, and dried floral arrangements in minimalist compositions. A woven pendant light fixture hangs from the ceiling in the center of the frame, adding a natural organic texture overhead.\n\nIn front of the sofa is a modern light-toned boho rug with subtle checkered patterns and fringed edges — it is minimal, textured, and clearly distinct from any patterned or overly decorative rugs. A rectangular light wood coffee table sits atop the rug, styled with a few ceramic vases and books in a carefully curated, editorial look. Natural oak flooring and soft shadows complete the light, airy, and Instagram-friendly atmosphere.\n\n🚫 Negative Prompt (to suppress trained rug + noise):\nfloral rug, oriental carpet, busy texture, clutter, heavy furniture, baroque, dark shadows, glossy floor, fantasy elements, cartoon style, mismatched decor",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "jpg",
  "guidance_scale": 2,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 35
}

Output Results

https://replicate.delivery/xezq/ShLqaEngc5biBJzDoGJOxhX1tcs2NZGyHpwPLBdS2T0EJ2IF/out-0.jpg

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 15
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Text-to-image generationImage-to-image translationMask-based inpaintingCustom aspect ratioLoRA supportMultiple model variantsAdjustable denoisingGuidance scale

Related Models

Vladu Image Generation

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

Oyadi Image Generation Model

A model for generating and editing images using text prompts with support for inpainting, img2img, and LoRA adjustments.

Mayo4 Image Generation

A model for generating and manipulating images based on text prompts and input images.