I recently found this free AI generator called Ideogram.ai. What makes Ideogram.ai unique? It handles text better than any other AI generator out there right now. It is still in its infant stage but creates images with the words you prompt (well, mainly.)
Check the samples below:
As seen in the samples, it can create phrases, alter font styles, and mimic styles you refer to in your prompt.
It can even design the type to look like the item you are describing:
Now, its flaws are usually related to space and image size. Use large words that can't fit properly into the area you requested, and you might see letters missing from that word. Like anything with AI, practicing to see what is understood and what causes errors will help you achieve the visual goals you set in your prompts.
Currently, the website is free. There is a timer between prompting that stops people from abusing the system with multi-requests -- so you do have to wait sometimes to submit your prompts. Like most AI generators based on Stable Difusion, you get 4 sample images per prompt. You can select the images you like and download them or share them with others.
I highly recommend you give Ideogram.ai a try. Link: https://ideogram.ai/
Jim Romer’s blog: character designs, writing picture books, and random thoughts!
Showing posts with label #AI. Show all posts
Showing posts with label #AI. Show all posts
Thursday, September 14, 2023
Wednesday, August 30, 2023
Sketch to Drawing - Introducing Promeai.com
Note: Links will open to a new page.
AI services I'll be sharing discoveries in AI, such as this free-to-use website Promeai.
It features several AI services, but for now I'm focusing on one in particular: Sketch Rendering.
Sketch Rendering is taking a sketch -- penciled, inked, or doodled image, and changing it into a 3D, realistic, or fully rendered image based on your drawing and text prompts. It still needs to be highly tuned. There is much to improve, and getting what you want is hard. That being said, the results are fascinating, and I can see great potential in AI doing this in the future.
Below is an inked sketch of a basket design I did years ago. It has enough detail to let the AI do its thing. I'm going to use my text description as follows: "(Yellow Moon Character with indent craters) (Easter basket) (red rocketship attached to a blue rope handle) (Plain white background)"
Note I use parentheses to group related words into phrases. On some websites, this helps the AI understand better. I could generate the following images by importing this image and typing the prompt. The coloring and detailing are still random, even though I specified what colors should be used. Again, this technology is in its infant stage, and there is much to improve. But the results of 2D to 3D are quite amazing, especially considering the mere seconds it takes to generate such images.
Bear in mind I did prompt the same sketch quite a few times (about ten times, generating about 30 images), and these three were what I consider to be the best of the bunch.
The most frustrating thing about using AI is control. There are SO MANY factors to consider.
You must practice your typing descriptions, learn the way AI thinks, and use other AI tools to work around issues that occur.
So, give the website a try. It's free. It's fun. There are many other tools to experiment with there. It could be better, but it is free.
Here's the direct link: www.promeai.com/
AI services I'll be sharing discoveries in AI, such as this free-to-use website Promeai.
It features several AI services, but for now I'm focusing on one in particular: Sketch Rendering.
Sketch Rendering is taking a sketch -- penciled, inked, or doodled image, and changing it into a 3D, realistic, or fully rendered image based on your drawing and text prompts. It still needs to be highly tuned. There is much to improve, and getting what you want is hard. That being said, the results are fascinating, and I can see great potential in AI doing this in the future.
Below is an inked sketch of a basket design I did years ago. It has enough detail to let the AI do its thing. I'm going to use my text description as follows: "(Yellow Moon Character with indent craters) (Easter basket) (red rocketship attached to a blue rope handle) (Plain white background)"
Note I use parentheses to group related words into phrases. On some websites, this helps the AI understand better. I could generate the following images by importing this image and typing the prompt. The coloring and detailing are still random, even though I specified what colors should be used. Again, this technology is in its infant stage, and there is much to improve. But the results of 2D to 3D are quite amazing, especially considering the mere seconds it takes to generate such images.
Bear in mind I did prompt the same sketch quite a few times (about ten times, generating about 30 images), and these three were what I consider to be the best of the bunch.
The most frustrating thing about using AI is control. There are SO MANY factors to consider.
You must practice your typing descriptions, learn the way AI thinks, and use other AI tools to work around issues that occur.
So, give the website a try. It's free. It's fun. There are many other tools to experiment with there. It could be better, but it is free.
Here's the direct link: www.promeai.com/
Subscribe to:
Posts (Atom)