Skillful AI Public Docs v1
SkillfulAI_Docs_v1.0
SkillfulAI_Docs_v1.0
  • Overview of Skillful AI
  • Introduction
    • AI Models
      • Types of AI models
    • Decentralization of AI
    • LLM Architectures
    • Current Challenges
    • Our Solution
  • Ecosystem Overview
  • Product Suite
    • Model Hub
      • Collaborative Mode
    • AI Builder
      • 1. Creating a Character
      • 2. Language Model
      • 3. Strategy
      • 4. Skills
        • List of Skills
      • 5. Memory
      • 6. Integrations
      • 7. Agent Info & Tasks
    • Agent Hub
    • AI Marketplace
    • Image Hub
    • Wallet
  • Tokenomics
  • Pricing
  • Links
  • Glossary
  • About Us
  • FAQs
  • Partnerships
Powered by GitBook
On this page
  • 1. Text-to-Image
  • Current Features
  • Advanced Customization Options
  • How the Image Hub's Model Was Fine-Tuned?
  • 2. Image-to-Image
  1. Product Suite

Image Hub

PreviousAI MarketplaceNextWallet

Last updated 21 days ago

Our Image Hub has two powerful tools: Text-to-Image and Image-to-Image.

1. Text-to-Image

It allows users to create high quality images. It is a fine-tuned version of model, and is optimized for generating comic style images.

This model was originally trained to generate the Skillful AI CyberCat NFT collection, which performs best with cartoon-style images. However, the model can be adapted for other styles with some experimentation.

Current Features

  • History Section: Users can view all previously generated images along with the prompts used. This feature helps users keep track of their creations and revisit past work.

  • Multiple Images: Users can currently generate up to 4 images simultaneously from a single prompt.

  • Pricing: At present, generating a single image costs 3 cents. For example, running one prompt with 4 variations will cost 12 cents.

Advanced Customization Options

Inference Steps

  • It controls the number of steps the model takes during image generation.

  • More Steps: Produces detailed and high-quality images but takes longer. Give more shadows, saturated colours and glossy effect. Works best for 3D character generations.

  • Fewer Steps: Quicker generation but may result in simpler natural outputs. Sometimes, images may appear simplistic or overly smooth.

  • Tip: Extreme values for inference steps or guidance scale may lead to overly saturated or distorted images. Start with middle ranges to balance detail and efficiency.

Seed Number (1-1000):

  • It ensures consistency or introduces variation in image outputs.

  • Same Seed: Reproduces the exact image style every time.

  • Different Seeds: Generates diverse styles.

  • For instance, if you use the same seed (e.g., 75) and input the same prompt (e.g., "a elephant wearing sunglasses”), the resulting images will be identical for that seed.

  • Seed feature is particularly useful for:

    • Consistency: Maintaining a uniform style across multiple images, such as creating a series featuring a animal, specific objects etc. in the same artistic style.

    • Variety: By changing the seed, you can explore different styles for the same subject.

Guidance Scale:

  • Adjusts how strictly the model follows the prompt.

  • Higher Scale: Aligns more closely with the prompt, potentially reducing creativity.

  • Lower Scale: Allows for more flexibility and imaginative results.

  • Extremes in guidance scale might lead to unusual or broken images, especially if the prompt includes elements outside the system’s training scope.

Comic Style Toggle:

  • Activates the comic/cartoon effect. This is optimized for the model’s training style.

How the Image Hub's Model Was Fine-Tuned?

The foundation of the Image Hub is Stable Diffusion XL (SDXL), an open-source model recognized for its exceptional image generation quality and flexible commercial licensing.

We enhanced the model’s capabilities for comic-style outputs through a process of fine-tuning using LoRA (Low-Rank Adaptation). This allowed us to adapt the model without altering its original weights, while retaining memory efficiency and cost-effectiveness.

Using LoRA, we added extra layers (specialized learnable matrices) to the model that focused on the comic style, making it more efficient without using a lot of memory. The training was done using advanced NVIDIA L4 GPUs through Google Colab Pro, a cloud-based service. We used Hugging Face diffusers library and the Accelerate framework to manage resources.

Through constant testing and improvements, the model was refined to generate high-quality comic-style images.

2. Image-to-Image

Skillful AI’s image editor lets you make targeted changes to any picture using simple controls. Just select the area you want to alter, pick the edit type, tweak a few settings, and generate the result.

  1. Mask Mode

Defines which part of the image your edits will affect:

  • User Provided: Paint your own mask to pinpoint exactly where changes happen.

  • Background: AI detects and masks everything behind the main subject.

  • Foreground: AI finds the primary subject and masks the rest so you can edit around it.

2. Edit Mode

Select how Skillful AI handles the masked area:

  • Inpaint (Removal): Erase unwanted objects and fill the gap with matching detail.

  • Inpaint (Insertion): Add new elements inside the mask based on your text.

  • BGSwap: Swap the background while keeping your subject unchanged.

  • Outpaint: Expand the canvas, and let the AI generate the surrounding context.

3. Basic Controls

  • Brush Size: Slide to change how much area each mask stroke covers.

  • Prompt: Describe what you want to add, remove, or modify (for example, “add a small cabin”).

  • Things to Avoid (optional): List any items you don’t want (for example, “no text or logos”).

4. Advanced Settings

  • Guidance Scale: Higher values force closer adherence to your prompt; lower values allow more natural variation.

  • Steps: Number of passes the model takes. More steps sharpen details but take longer.

  • Dilation: Expands the mask slightly for smoother edges.

  • Seed: A fixed number guarantees the same result each time; random produces new variations.

Stable Diffusion XL (SDXL)