In the midst of the ai revolution, a single question was burning in my brain: Can free ai image generators create a photorealistic image based on the following message?
Cat picking daisies
Note that this devilishly difficult task includes three parts, two of which are not particularly difficult: the cats and the daisies. It’s the action that was difficult.
Nevertheless, the results were intriguing. Although image quality varied widely, the variety of imaginative responses is encouraging for the use of ai image generators as tools for creative expression. While all images included here are the first iteration, they can be considered a starting point, to which users can apply carefully designed cues to shape and edit the results.
To use the Adobe Firefly image generator, a free account is required. Four aspect ratios and dozens of styles, themes and techniques are provided. Users’ free generative credit counts are reset each month automatically, albeit with a somewhat complicated scheme for tracking those credits.
RESULTS: You don’t want to meet any of these cats in real life.
Image 1 of 4
This ai image generator automatically detects if you’re signed in to a Microsoft account, making it easy to start creating images right away. Start with 100 credits and then apply the reward points accumulated in your MSN account to get more. Save, download or customize your images. The platform applies controls to prevent the generation of potentially harmful images and includes a modified Bing icon in the lower left corner of each image to indicate that the image was created with Image Creator.
RESULTS: Perhaps the most realistic set of images was the one generated by the Bing platform. Not only were the faces of the cats and flowers very photorealistic, but also the action depicted approached the immediate challenge. To be fair, it should be noted that by depicting only close-ups of cat heads, with no limbs or bodies, Bing narrowed the scope of the difficulty. Maybe this is part of his intelligence!
Image 1 of 4
This relatively simple site is easy to use, but slower than average, offering just three styling options for free users. For faster results, purchase a plan priced between $5 and $20 per month. Free results are automatically generated on a 3x grid with nine images.
RESULTS: Craiyon’s algorithm had trouble with the cats’ eyes and faces and specific background details. However, credit where credit is due: as ungainly as the results were, Craiyon at least attempted to portray the action of the “cat picking daisies” with paws, mouths, and paws, rather than simply focusing on nouns (cat, daisies) and avoiding the verb (collect).
Image 1 of 2
With an image look picker, as well as dozens of free and paid styles to choose from, Deep ai also includes an ai chatbot. While the site is easy to use, the images may provoke responses from users such as “Where is the cat?” to “Are they two bodies, one head?” to “Straight from the uncanny valley to your computer!” The so-called Genius Mode might work better, for $4.99 per month.
RESULTS: One of the four attempts produced a photorealistic feline head, which may or may not have been attached to two bodies (you judge). On the other hand, photorealism is overrated. Users are advised to follow the slightly surreal flow.
Image 1 of 4
To use Fotor ai Image Generator, create an account or sign in to Google. After the first free images, users will need to purchase credits or a subscription. Choose from five aspect ratios and dozens of styles. Do you need inspiration? Explore the impressive library of images generated by other users.
RESULTS: Three out of four images were fairly photorealistic depictions of cats, grass, and daisies. Please note that the software has more problems with the eyes when the view is not front-facing.
Image 1 of 4
The polished Imagine ai website has a strong base of six million users and 70 million generated images. The free image generation options are limited to a 1:1 aspect ratio and eight styles.
RESULTS: High quality flowers, heads and cat faces, with somewhat disproportionately small bodies.
Image 1 of 3
Night Cafe offers five different text-to-image algorithms, with varying results. In general, the highly imaginative approach is better suited to flights of fancy than photorealistic images. A strong user community supports a chat room, robust image library, contests, and more. Users can accumulate a fairly generous credit package by performing actions such as posting their images or liking others’ images.
RESULTS: From cubist nightmares (disfigured faces and strange eyes) to women with cat ears, Night Cafe’s ai-generated images are not without charm.
Image 1 of 3
Quite slow, but your place in the queue is always visible, as well as the expected remaining time. Fortunately, although the site proclaims “Freedom: There are no limitations on what you can enter,” the graphical word prompts only returned a black image square.
RESULTS: While the cats depicted are fairly proportioned, detailed, and generally realistic, they look more like an illustration than a photograph. However, if you have time to wait, the free version of Stable Diffusion is a good option to try. Pro tip: The time of day is a big factor when it comes to waiting in line. Avoid rush hours.