Live data from Hacker News

Tailor-made AI image generation

strmr.com

1–10 of 18 posts

Re: Tailor-made AI image generation

#2
Neat concept. Although I do think the homepage could maybe be improved. The main thing is it contains pretty minimal and vague information which makes it harder for people understand the product.

Also, when it says tailor-made does it mean that there is a human prompt engineer tuning the images for you? Or does it just mean that the AI generated images are custom, but there's no human prompt "tailoring" done for you?

Re: Tailor-made AI image generation

#5

Text Inversion as a Service?

Yep, that's exactly what it is. I can vouch that it really works. Pricing is $3 to run a fine tune, and then generations are "currently" free and unlimited.

I dig it, because I couldn't be bothered to run a colab notebook, but it is super-fun to play with.

Re: Tailor-made AI image generation

#6
post #5

Text Inversion as a Service?

Yep, that's exactly what it is. I can vouch that it really works. Pricing is $3 to run a fine tune, and then generations are "currently" free and unlimited. I dig it, because I couldn't be bothered to run a colab notebook, but it is super-fun to play with.

What is the value add compared to other free alternatives?

Re: Tailor-made AI image generation

#9
post #2

Neat concept. Although I do think the homepage could maybe be improved. The main thing is it contains pretty minimal and vague information which makes it harder for people understand the product. Also, when it says tailor-made does it mean that there is a human prompt engineer tuning the images for you? Or does it just mean that the AI generated images are custom, but there's no human prompt "tailoring" done for you?

Indeed we're working on that and explaining the technology behind is one of the things we're working on. Currently we're training a Stable Diffusion image-generation model, to the custom images that the user provide so that he can generate images of his specific subject consistently. This relies on a paper by Google called Dreambooth. So thank you mainly to Nathaniel Ruiz
Post reply on HN