Since we’ve seen how to make a consistent character, we can now try animating them. I said this was an area I wanted to delve into in my follow up to the consistent character post. I had a lot of fun animating stable diffusion characters, as you can see below in these stable diffusion animations. Results The Flow I made a script that would work with ControlNet. This script does several things. First it takes…
Using multiple types of generative AI together can be complicated. This is especially true if you want images inline with text. The text generation and image generation needs to be synced, and what is described in the text might not make for great images. Wading through all of that text to figure out what the prompt should be is time consuming. Here I’ll go through a method of making GPT give us the image it…
Theming is ‘The woman in the red dress’ for this one. Maybe that reference dates me. We got a lot of comments and interest for the previous post on characters with controlnet in Automatic1111 web ui running on runpod.io. So here is a follow up to the comments and questions. Extra Long One comment asked if we could make an image that was just extra long with all the poses we wanted included. We gave…
You don’t need to be an AI image generating wizard to want to upscale images. You may simply want to enlarge an image to make a high quality print or you have older digital photos that were taken at lower resolution and wish to increase their size for modern use. For those who do generate images with AI, many models work best at lower sizes such as 512×512 or 768×768. Or perhaps your hardware struggles…
There are other tools out there that allow the integration of Stable Diffusion, ChatGPT, and Text to Speech (TTS) into Unity, but this guide is intended to make integrating them all very simple. The below script doesn’t have the best coding practices, but it is an easy place to start with Unity AI integrations. Start By Getting All the Service Keys You of course will have to get your own keys from each service: Get…
GPT4 for stories is a vast improvement. The coherency of 3 wasn’t all that good, and 3.5-turbo (also known as ChatGPT) still left something to be desired. The upgrade for GPT4 over ChatGPT (3.5-turbo) is a larger upgrade than the DaVinci 2 to 3 change for GPT3. Some of the issues with 3 and 3.5-turbo that are better in GPT4 An Example with GPT4 vs. GPT3.5-turbo (ChatGPT) Prompt: Write a long chapter in the following…
One of the largest drawback to image generating AIs is that it is hard to get a consistent character. In this article I’ll explain how I have used a set of tools to overcome that impediment and make an AI character generator. Getting a set of six views of the same character Below is a set of images I generated using Stable Diffusion 1.5, Char Turner V2, and Control Net with Open Pose. These images…
When doing research to write my Ultimate Guide to All Inpaint Settings, I noticed there is quite a lot of misinformation about what what the different Masked Content options do under Stable Diffusion’s InPaint UI. To help clear things up, I’ve put together these visual aids to help people understand what Stable Diffusion does when you select these options, and how you can use them to get the AI generated images you want. What are…
When doing research to write my Ultimate Guide to All Inpaint Settings, I noticed there is quite a lot of misinformation and confusion over what denoising strength actually does. To help clear things up, I’ve put together these visual aids to help people understand what Stable Diffusion does for different Denoising Strength values, and how you can use it to get the AI generated images you want. What is Denoising Strength? When a user asks…
Sampling steps is the number of iterations that Stable Diffusion runs to go from random noise to a recognizable image based on the text prompt. As an extremely general rule of thumb, the higher the sampling steps, the more detail you will add to your image at the cost of longer processing time. However, what the optimal number of sampling steps for you and the output image you’re trying to generate is dependent on many variables,…