Text and images go hand in hand. A book is very text oriented, while games accessed through the Slotocash login are very visually oriented. And other times, an author (or creator) uses a combination of text and image to get a point across.
On this page
How to create images from text descriptions using Bard?
No, it cannot. “I apologize that I cannot generate images yet,” Bard responded. “I am still under development and learning how to generate images.”
On the other hand, when I asked for the translation of a list of vocabulary words, it returned an image for each of the words. That is a nice feature, but in this specific list, I did not want images, so I had to add to my prompt, “no images”.
How to create images from text descriptions using Dall E 3 or ChatGPT?
ChatGPT does allow you to create images from text description, but it is not free. So if you try to create an image from the free version of ChatGPT you will not get an image. You will just get an image description.
DALL·E 3 understands significantly more nuance and detail than our previous systems, allowing you to easily translate your ideas into exceptionally accurate images.
DALL·E 3 is now available to all ChatGPT Plus and Enterprise users, and will be available via the API and in Labs later this fall (October 2023, this month).
Modern text-to-image systems have a tendency to ignore words or descriptions, forcing users to learn prompt engineering. DALL·E 3 represents a leap forward in our ability to generate images that exactly adhere to the text you provide. Here are some examples of prompts that can be used to generate an image:
- A bustling city street under the shine of a full moon.
- The sidewalks bustling with pedestrians enjoying the nightlife.
- At a corner stall, a young woman with fiery red hair, dressed in a signature velvet coat, is haggling with a grumpy old vendor.
- The grumpy vendor, a tall sophisticated man, is wearing a sharp suit, sports a noteworthy mustache, and he is animatedly conversing on his steampunk telephone.
Sorry, but when I look at that description, human creativity is still required to get the final result. Submit the same prompt, and you will get different results.
Even with the same prompt, DALL·E 3 delivers significant improvements over DALL·E 2.
DALL·E 3 is built natively on ChatGPT, which lets you use ChatGPT as a brainstorming partner and refiner of your prompts. Just ask ChatGPT what you want to see in anything from a simple sentence to a detailed paragraph.
When prompted with an idea, ChatGPT will automatically generate tailored, detailed prompts for DALL·E 3 that bring your idea to life. If you like a particular image, but it’s not quite right, you can ask ChatGPT to make tweaks with just a few words.
DALL·E 3 will be available to ChatGPT Plus and Enterprise customers in early October. As with DALL·E 2, the images you create with DALL·E 3 are yours to use and you don’t need ChatGPT permission to reprint, sell or merchandise them.
DALL·E 3 has mitigations to decline requests that ask for a public figure by name.
DALL·E 3 is designed to decline requests that ask for an image in the style of a living artist. Creators can now also opt their images out from training of DALLE future image generation models.
Can search engines determine if an image was generated with DALLE?
Determining if an image was generated with DALLE is still in the development stage.
How much does it cost to create images with DALLE?
The cost of Dall-e credits is $15 for 115 credits. That works out to a price of about $0.13 per Dall-e credit. Dall-e users can purchase credits to top up their accounts from within the Dall-e interface in OpenAI labs. Payments are billed alongside the use of other OpenAI services like GPT-3.5
Each Dall-e credit allows you to create one “generation” using the system. This can include creating images based on Dall-e prompts, editing an image you upload to the system or creating additional variations on an existing image.
Any operation that requires Dall-e to do any kind of processing, or causes it to make something new, costs a credit.
Note that each credit doesn’t necessarily correlate with the cost of an individual image made by Dall-e. Prompt-based image generations, for example, yield four images each. If you choose only one of those, your newly-generated image will cost you $0.13.
If you can find a use for all four images generated by your prompt, though, the cost per image drops to $0.0325.
Since prompt intent can be hard to interpret, Dall-e often tries out multiple potential intents in order to give the user options.
In short, any operation you have Dall-e perform costs one credit, even if the operation returns more than one actual image.
What is ChatGPT Pro and why should I buy it?
ChatGPT Pro costs $20/month, so the obvious questions is if it is worth buying.
One major feature of the Pro Membership is that you can generate images from within ChatGPT Pro. If you try to do that within ChatGPT (standard version), you will just get a detailed description of your prompt.
Example Prompt: Create an image of a girl playing piano, sitting by a window, on a sunny day, and a kitten sitting next to the girl on the piano bench.
I’m a text-based AI and unable to create visual images or drawings. However, I can provide you with a description that you can use as inspiration for an image or share with an artist to bring your vision to life:
In the image, a young girl with a bright smile is sitting at a grand piano, positioned near a large, sunlit window. The room is filled with warm, golden sunlight, casting long, inviting shadows. The girl’s fingers delicately press the piano keys, her posture reflecting the grace and concentration of a skilled pianist.
She is dressed in a soft, pastel-colored dress, and her long, flowing hair is gently lit by the sun’s rays. Her eyes are closed as she immerses herself in the music, and her expression is one of pure joy. Sheet music is scattered across the piano’s music stand, evidence of her dedication to her craft.
On the piano bench beside her sits a fluffy, playful kitten. The kitten is looking up at the girl with curiosity, its tail playfully swaying. The contrast of the girl’s focused elegance and the kitten’s carefree spirit creates a heartwarming scene that captures a perfect sunny day of music and companionship.
Summary
I have personally seen projects that used DALLE-3 images. A child wrote a story, and used DALLE-3 to create images for her story. The end result was quite impressive.
But I had tried myself to use DALLE-3 to get an image generated, and I quickly used up my free credits trying to figure out how to create prompts to get the image results you are looking for.
So expect to “waste money” as you figure out prompt creation to create images. But once you get the hang of how to create prompts, you will not need as many revisions and the costs of image generation will be more reasonable.
