Skip to content

Outpainting

Video Lecture

Section Video Links
Outpainting Outpainting Outpainting 

 (Pay Per View)

You can use PayPal to purchase a one time viewing of this video for $1.49 USD.

Pay Per View Terms

  • One viewing session of this video will cost the equivalent of $1.49 USD in your currency.
  • After successful purchase, the video will automatically start playing.
  • You can pause, replay and go fullscreen as many times as needed in one single session for up to an hour.
  • Do not refresh the browser since it will invalidate the session.
  • If you want longer-term access to all videos, consider purchasing full access through Udemy or YouTube Memberships instead.
  • This Pay Per View option does not permit downloading this video for later viewing or sharing.
  • All videos are Copyright © 2019-2025 Sean Bradley, all rights reserved.
Video Timings 00:00 Introduction to Outpainting and its core purpose
00:35 Setting up ComfyUI for outpainting a half car
01:10 Applying the prompt and first image generation
01:45 Fixing the sharp line with the Grow Mask
02:15 Further expanding the car image and adjusting size
02:50 Starting a new outpainting example with a fish
03:25 Refining fish image by adjusting prompt and expansion
04:00 Understanding feathering and visualizing the effect using a mask
04:40 Experimenting with different fish types and feathering impact
05:15 Addressing the persistent white background issue in outpainting
05:50 Combining outpainting and inpainting for background editing
06:40 Final results and refining the combined inpainting process

Description

Outpainting in AI image generation refers to the process of extending an image beyond its original borders using a generative model.

Given an existing image and a prompt, the model predicts and fills in new visual content that seamlessly matches the original style, lighting, and context.

It's useful for creating wider scenes, changing aspect ratios, or creatively expanding artwork or photos.

Outpainting relies on the model’s understanding of visual context to generate believable content that aligns with the existing image, essentially "imagining" what lies beyond the original frame.

In this lesson you can use your own 512x512 images, or copy/paste these images below into into your ComfyUI when necessary in the video.

half of car

half a fish

incomplete fish with no background