ImageToPromptAI
Image to prompt generator
| About | Details |
|---|---|
| Name: | ImageToPromptAI |
| Submited By: | Ulises Ankunding |
| Release Date | 1 year ago |
| Website | Visit Website |
| Category |
Generate Text Prompts for Stable Diffusion from images using A.I and Reproduce Comparable Image/Painting Variations
I really like this idea. This can be very useful if you are inspired by an image but don't have an idea of how to generate similar images with AI. At least, you don't have to do everything from scratch. I tried it for 2 images, one for a gnome in a hot air balloon and the other was an image of Flash from DC comics. Here are the two prompts: Prompt 1: a painting of a gnome in a hot air balloon, a storybook illustration by Justin Gerard, cgsociety contest winner, fantasy art, storybook illustration, detailed painting, whimsical Prompt 2: a man in a red and yellow costume is flying, a comic book panel by Lichtenstein, featured on deviantart, superflat, dc comics, flat colors, flat shading Although I think the second prompt could have been much better, still this is a good starting point. Also, I am curious on what technology you are using under the hood to get these results? Congratulations on the launch!! @imadchakri
1 year ago
How does it compare to lets say adobe firefly in terms of accuracy. I for one cannot use your product because it asks me to buy credits to use it. I would certainly want to know what I am buying before spending 20 odd dollars. Maybe if you have 5 free images/day, people would know, me included, how the results turn out.
1 year ago
The resulting prompt is pretty accurate. I have tried with two versions of the same photo, one with its original background and one without it (transparent) and I received two different meaningful prompts accordingly. The pricing is a bit off, in my opinion: it makes the top tier the best option but that might discourage the occasional user because they might never be using 500 prompts while the entry tier at 20 cents per prompt seems a bit overpriced in comparison. The "issue" with AI images is that the generated photos are still far away from usable in a professional environment and several tries and fine-tuning are required before getting a decent result; this app certainly create good prompts and it has room for improvements but ultimately its value will increase in time when AI generated images will also get better. To me in order to keep that pricing model additional features need to be added. For example, if it generates the prompt, why not offering also the change to use it on site to generate the next photo? Or why not transforming it into an API that can be integrated with existing AI image generators? Just my idea, of course. One thing I'd definitely consider adding though is suggesting aperture, focus and other tech camera settings, when user upload a real photo. I don't know how the system works in the background, hence if this is easily implementable or not, but in order to get a realistic photo back from an AI generator, those parameters and especially the correct ones are paramount. All in all, this has potential and it is well crafted so considering that this is a first launch, I definitely support it.
1 year ago
I would love to try this, but with zero credits makes it impossible to decide if it's worth or not. I might be wrong of course, but my 2 cents go for giving one credit away at least at launch, if you would like to receive reviews and get traction. I try tens of PH apps every day, and unfortunately I have to skip those which are completely behind a pay wall, unless they are something I'm really in need of. Said this, I can see real world cases for it assuming that the generated prompts are in line with expectations. So, grats on the launch: supporting for the idea.
1 year ago