Image Hub
Last updated
Last updated
Our Image Hub has two powerful tools: Text-to-Image and Image-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.
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.
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.
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.
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.
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.
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.
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”).
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.
