Kenner Super Power

Unleash your creativity with Kenner Super Power, a powerful image generation and editing model. Let's explore what this AI model can do for you!

Platform: Replicate

Diffusion Image GenerationText-to-ImageImage InpaintingLoRA Support

105 runs

H100

License Check Required

🚀Function Overview

Generates and edits images through text prompts, image inputs, and masks using configurable diffusion models supporting LoRA adaptations.

Key Features

Text-to-image generation with trigger word activation
Image-to-image transformation with adjustable strength
Inpainting capabilities using image masks
Multiple inference models (dev/schnell) for quality/speed tradeoffs
LoRA weight loading and scaling for style adaptation
Custom resolution/aspect ratio control
Output quality/format configuration

Use Cases

•Generating styled images from text descriptions
•Editing existing images via inpainting
•Converting sketches to refined artwork
•Creating themed content with LoRA adaptations

⚙️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

{
  "image": "https://replicate.delivery/pbxt/N7fqrtbcdfZ4muJ6A3y2wbrxZmAur9Tgc5GvxMMf52ufXX7A/out-1%20%281%29.webp",
  "model": "dev",
  "prompt": "Head & Hair\nHair: Long, voluminous, curly blonde hair with prominent ringlets. Worn loose.\n\nHeadband: red headband around her forehead, visible in the side and back views. Her hair above the headband it bundled by the headband and pushed back, but somewhat high, with a small blonde curl falling down over the headband in the front. Below the headband her hair is lose. Her hairstyle slightly ressembles a mullet.\n\nFacial Features: Classic comic book style with bright eyes, full lips, and a confident expression. Her teeth are showing slightly.\n\nCostume (Upper Body)\nTop: Blue long-sleeve fitted top with red trim at the neck.\n\nLogo: Large red and yellow S shield on her chest (front view). The red part of the logo extends out to the cape area and completely covers her shoulders. There are two fine yellow lines on the top left and top right side of the logo, which separate the logo from the red area.\n\nCape: Red on the outside, white lining. Shoulder-attached and flows down her back. In the back view, it’s open to show the full yellow “S” symbol.\n\nCostume (Lower Body)\nSkirt: Short, pleated, bright red skirt with dynamic folds suggesting movement.\n\nBelt: V-shaped belt sitting at the waist. The V is pointing down and spans the waist (because it's a belt) \n\nLegwear & Boots\nBoots: Red knee-high boots with yellow upward-pointing triangular designs at the top.\n\nBare Legs: No tights or leggings—legs are bare.\n\nColor Scheme\nPrimary Colors: Bright red, yellow, and blue (classic Superman family palette).\n\nSecondary Detail: White cape interior, yellow belt and boot trim.\n\nPose and Style\nThe figure stands confidently, with fists clenched or on hips.\n\nBody proportions are athletic and slightly stylized—broad shoulders, slim waist, muscular but not exaggerated.\n\nThe style reflects 1980s superhero comics: clean lines, bright flat colors, bold shapes.\n\na full body render of a kennersuperpowers action figure \n",
  "go_fast": false,
  "lora_scale": 1.05,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.6,
  "extra_lora_scale": 1,
  "num_inference_steps": 32
}

Output Results

https://replicate.delivery/xezq/gmQal8XAUpYYLxWd0IlXgDkDYCU9e8JIeDkf3IhJMvNRFcmpA/out-0.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 105
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Diffusion Image GenerationText-to-ImageImage InpaintingLoRA SupportImage-to-Image TransformationConfigurable Diffusion ModelsCustom Resolution ControlOutput Quality/Format Configuration

Related Models

ECG Kidjump Image Generator

A model for image generation and editing using prompts, input images, and masks with support for LoRA adapters.

Flux Prehistoric Art

A model for generating images with a prehistoric art style through text prompts and image manipulation features.

Divin AI Image Generation

Un modèle qui génère des images qui ressemble à 100/100 Divin