SeaArt Guide
How to SeaArt AI - Office Tutorial
How to SeaArt AI - Office Tutorial
  • ✨How to Use an AI Image Generator
  • ✨1-SeaArt AI Basic Page
  • ✨2-SeaArt AI Basic Function
    • 2-1 Text to Image
    • 2-2 Image to Image
    • 2-3 ControlNet
    • 2-4 AI Apps
      • How to publish as App
      • Swift AI Apps
    • 2-5 AI Characters
      • How to create your own character?
      • Character Description Writing Tips
      • Conversation Tips
    • 2-6 Models
    • 2-7 Post
    • 2-8 AI Video Generation
      • Txt2Vid
      • Img2Vid
      • Camera Movement
      • Start and End Frames
    • 2-9 AI Audio
    • 2-10 Workflow
      • Text to Image Workflow
      • IMG2IMG+Partial Repainting
      • Core Nodes
      • Tips
    • 2-11 Canvas
    • 2-12 LoRA Training
      • Flux Lora Training
  • ✨3-Advanced Guide
    • 3-1 Principles of AI art
    • 3-2 LoRA Training (Advance)
      • How To Create Dataset For Training
    • 3-3 Workflow Guide
      • Image Conversion
      • Inpainting
    • 3-4 Canvas Guide
    • Composite Poster
  • ✨4-Parameters
    • 4-1 Model
    • 4-2 Mode
    • 4-3 Basic Settings
    • 4-4 Advanced Config
    • 4-5 Advanced Repair
    • 4-6 Complete Prompting Guide
    • 4-7 Prompt Edit | Keyword Blending Guide
  • ✨5-Practical Examples
    • AI Influencer
    • LOGO Design
    • E-commerce Poster
    • How To Make Multiple Characters
    • Prompt Templates
    • How to Maintain Character Consistency
    • Useful Prompts
  • ✨6-Permanent Events
    • SeaArt.AI Creator Incentive Program
      • Creator Incentive Program FAQ
    • High-Quality Models Recommendation
      • SeaArt Infinity
      • Stable Diffusion 3.5
      • SeaArt Realism
      • NOOBAI XL
      • T-Ponynai3 V6
      • Counterfeit V3.0
      • Temporal Paradox Mix
    • High-Quality AI Apps Recommendation
    • High-Quality Character Recommendation
    • High-Quality Workflow Recommendation
  • ✨7-FAQ
Powered by GitBook
On this page
  • What is Image to Image?
  • Analysis of Img to Img Parameters
  1. 2-SeaArt AI Basic Function

2-2 Image to Image

Ready to transform images? Step into the world of image-to-image and learn its parameters and workflow.

Previous2-1 Text to ImageNext2-3 ControlNet

Last updated 9 months ago

In the practical application of AI painting, due to the uncertainty of the initial images produced by the model, the actual controllability of the output images is not high. Subsequently, we can use the "Image to Image" function to modify the pictures towards our desired direction, thereby enhancing the controllability of the generated images.

What is Image to Image?

The "Image to Image" function is an AI-based image generation technology that allows users to generate new images based on an existing picture combined with text descriptions. This technology is significant because it can create new visual content by mixing image and text prompts according to the specific needs of users.

Simply put, the process of considering both the prompt words and the image information in the reference picture and then drawing is what constitutes the image-to-image generation.

Analysis of Img to Img Parameters

Intelligent Analysis

Automatically inferring matching prompts based on the provided image, as well as a model that matches the image. However, the prompts generated by intelligent analysis may contain incorrect prompts, so it is recommended to manually perform a second screening. This function primarily serves as a reference for writing prompt words.

Workflow of Img to Img

Workflow: Upload Reference Image - Set Model Prompts - Set Parameters - Generate

After uploading the reference image, open intelligent analysis, which will automatically fill in the prompts, Model, and image size. It is recommended to readjust the prompts according to actual needs. The parameter settings are the same as for generating initial images. Finally, click to generate the image, and AI will create a new image based on the reference picture and the user's instructions.

*The larger the redrawing extent, the greater the difference from the original image. It is generally set between 0.4-0.8.

Denoising Strength: This parameter controls the degree of divergence in the redrawing process based on the original image. The higher the value, the more freedom the model has during the redrawing process, and the greater the difference between the drawing result and the original reference image.

When the Denoising Strength is too high, it becomes difficult to associate the drawn image content with the original image, hence, we typically keep the value of the redrawing extent between 0.4 and 0.8.

Partial Repainting

Partial Repainting allows for modifications and adjustments to specific areas within an image. This feature is particularly suited for fine-tuning local details. It also requires the addition of prompts to guide the modification content. This is used when the majority of the image content is satisfactory, but there is a need to adjust some detail elements.

After uploading the image, click the brush on the right to enter the Partial Repainting area. Then, you can smear the image. After smearing, fill in the prompts for the smeared area in the prompt box.

After using Partial Repainting, only the selected area has been redrawn, while the other areas remain unchanged.

✨
Before and after comparison of turning an image into anime style
SeaArt intelligent analysis feature
Four examples of AI-generated images of a girl
Partial repainting an AI image
Adjust crown within an AI-generated image