Friday, July 28, 2023
Is DALL-E 3 About to Be Released?
Tuesday, July 25, 2023
ChatGPT Formula for Generating Prompts
I recently came across a YouTube video by a creator named Monice in which she gave a formula that would enable one to use ChatGPT as an image generator for Midjourney. The given formula to be entered into ChatGPT reads as follows:
"Here’s a Midjourney formula for you to understand.
‘/imagine prompt: [Image we are prompting], [5 descriptive keywords], [Camera type], [Camera lens type], [time of the day], [focal distance], [style of photograph], [by photographer name] –ar x:y Reply ‘yes’ if you understood the formula."
I decided to give it a try and ChatGPT quickly furnished me with the following parameters:
"/imagine prompt: [Image we are prompting], [5 descriptive keywords], [Camera type], [Camera lens type], [time of the day], [focal distance], [style of photograph], [by photographer name] –ar x:y
[Image we are prompting]: This is the main subject or content of the photograph that will be used as a basis for the prompt.
[5 descriptive keywords]: Five words that describe the main elements or characteristics of the image.
[Camera type]: The type of camera used to capture the photograph.
[Camera lens type]: The specific lens used on the camera to capture the image.
[time of the day]: The specific time of day when the photograph was taken (e.g., morning, afternoon, evening).
[focal distance]: The distance at which the camera's lens is focused when capturing the image.
[style of photograph]: The artistic style or approach used in the photograph (e.g., abstract, portrait, landscape).
[by photographer name]: The name of the photographer who took the picture.
–ar x:y: The aspect ratio (ar) of the photograph, represented by 'x:y'"
I in turn provided the following information:
"Here are the specifics for each parameter as numbered above: 1. image we are prompting = A depressed young woman sits on wet floor in an unfurnished darkened basement and stares forlornly at a tiny skylight high above her head; 2. five descriptive keywords = depressed, melancholy, darkened, forlorn, muted; 3. camera type = nikon df dslr; 4. lens type = nikon 23mm wide angle lens; time of day = 4pm EST; focal distance = 5 feet; style of photograph - artistic vintage color; name of photographer = paola m franqui; aspect ratio = 1620 px wide by 1080 px high"
ChatGPT then issued the following prompt:
"A depressed young woman sits on the wet floor in an unfurnished darkened basement and stares forlornly at a tiny skylight high above her head. Keywords: depressed, melancholy, darkened, forlorn, muted. Camera type: Nikon DF DSLR. Lens type: Nikon 23mm wide-angle lens. Time of day: 4 PM EST. Focal distance: 5 feet. Style of photograph: Artistic vintage color. By photographer Paola M Franqui. –ar 1620:1080"
Since I do not currently have an account on Midjourney, I instead entered the prompt into Clipdrop Stable Diffusion XL which generated four images from it, two of which are shown here.
I thought the images were very much in line with what I had been looking for, though I don't know if it really had been necessary to go through ChatGPT to get them.
Monday, July 24, 2023
Using Poetry for AI Prompts
As I'm always in search of new ideas for AI imaging prompts, it recently occurred to me to simply enter random lines of poetry and then wait to see what a particular AI model would make of them. Rather than work from masterpieces of literature, I instead focused on poetry that contained the most vivid imagery. Accordingly, the two images shown here were generated by Clipdrop Stable Diffusion XL from the opening lines of the 1912 poem Medusa by Clark Ashton Smith, always one of my favorite Weird Tales authors of whom no one less than H.P. Lovecraft once wrote: "In sheer demonic strangeness and fertility of conception, Clark Ashton Smith is perhaps unexcelled." And on that score who would know better than Lovecraft?
Medusa itself is contained in The Star-Treader and other Poems, available as a free download from Project Gutenberg, and the lines in question read as follows:
"As drear and barren as the glooms of Death,
It lies, a windless land of livid dawns,
Nude to a desolate firmament, with hills
That seem the fleshless earth's outjutting ribs,
And plains whose face is crossed and rivelled deep
With gullies twisting like a serpent's track.
The leprous touch of Death is on its stones,
Where for his token visible, the Head
Is throned upon a heap of monstrous rocks,
Grotesque in everlasting ugliness,
Within a hill-ravine, that splits athwart
Like some old, hideous and unhealing scar."
Pretty strong stuff, isn't it? And perfect for the use to which I put it.
My college degree was in English lit; and so I have, even many years later, a wide familiarity with world poetry from which to draw future inspiration. It will be interesting, to me at least, to see what I can come up with.
Friday, July 14, 2023
Is Lexica the Best AI Imaging App?
Monday, July 10, 2023
How Good Is Leonardo AI?
Thursday, July 6, 2023
Midjourney 6.0 Arriving Soon?
According to an article in Forbes, which in general is a fairly reliable source of information, AI imaging app Midjourney will release version 6.0 before the end of July. The article unfortunately did not contain any information on what features the new version may offer. It did, however, describe in a fair amount of detail two new features in the current version 5.2 and also posted examples to illustrate the results obtained with them.
The first of these new features is the ability to create panoramic images. According to Forbes, it works as follows:
"When a regular image is upscaled to full resolution, the user gets the option to pan the image left, right, up or down. This effectively extends the image in the chosen direction, with the AI filling in the empty space.
Images can continue to be extended beyond one iteration, although the wider and wider aspect ratio becomes problematic.
Users can also enter Midjourney’s Remix mode and change the prompt at the same time as extending the image, effectively letting them create panoramic photo stories."
The second new feature is Weirdness. As the name would imply, this feature allows users to dial in various degrees of "weirdness" into generated images on a scale of 0 to 3,000. How useful Midjourney subscribers will find this feature will obviously depend on their individual styles of creativity. Those who favor a straightforward approach to image generation will most likely opt not to work with it that often while those seeking to create the unusual and fanciful may find it quite helpful in achieving their goals.
Wednesday, July 5, 2023
Clipdrop Uncrop
Tuesday, July 4, 2023
Picsart AI GIF Creator
“A world of untapped GIF potential awaits at your fingertips. No longer will you have to rely solely on recycled content or endlessly search for the perfect GIF to convey your emotions or thoughts. Our AI GIF Generator empowers you to express yourself with unprecedented originality, opening up a realm of endless creativity. The GIF game will never be the same again.”
Monday, July 3, 2023
Text-to-Image AI Generated Prompts: ChatGPT vs. Google Bard
"Prompt: Create an AI-generated image that captures the essence of 'beauty' in nature.Description: Imagine a serene landscape where beauty abounds. The image should showcase a harmonious blend of colors, shapes, and textures that epitomize the concept of beauty. Incorporate elements such as a stunning sunset or sunrise, vibrant flowers, majestic mountains, a serene lake, or any other natural elements that evoke a sense of awe and wonder. The goal is to convey the breathtaking beauty found in the natural world through an AI-generated image. Let your creativity and the power of AI bring this beauty to life!"
"Sure, I can do that. Just give me a word and I will generate a prompt for you. For example, if you give me the word 'cat', I might generate a prompt like this:A realistic 4k image of a cat sitting on a windowsill, looking out at the city skyline. The cat is wearing a red bow tie and has a content expression on its face."
"I can also generate prompts that are more abstract or creative. For example, if you give me the word 'dream', I might generate a prompt like this:A surreal image of a dreamscape. The landscape is made up of strange and colorful shapes, and there are floating objects in the air. A figure is walking through the dreamscape, their face obscured by a mist."
"A realistic image of a field of flowers in full bloom. The flowers are a variety of colors, and they are swaying in the breeze. The sun is shining brightly, and the sky is a clear blue."
"A detailed image of a butterfly's wing. The wing is covered in intricate patterns, and it is reflecting the light in a beautiful way. The butterfly is perched on a flower, and its wings are slowly opening and closing."
"A stunning image of a sunset over the ocean. The sky is ablaze with color, and the clouds are reflecting the light in a magical way. The waves are crashing on the shore, and the seagulls are soaring overhead."
"A mesmerizing image of a nebula. The nebula is made up of gas and dust, and it is glowing with a beautiful light. The nebula is located in a distant galaxy, and it is millions of light-years away from Earth."
"A serene image of a mountain lake. The lake is surrounded by mountains, and the water is a clear blue color. The sun is shining brightly, and the trees are reflected in the water."