Why this service?

This is life changing technology, the next generation of children will take these generative AI models for granted. Imagine custom video games, dynamic movies, custom ads, augmented reality sessions with anyone,etc. We are just seeing these innovations start to become prioritized. In order to help accelerate this future, we created this software to make it easy to use for anyone right now. We are constantly integrating the latest innovations to make sure you always have access to it.

Do you have an API?

Yes, we do! api reference

Where do I get my API key?

HERE

What kind of images should I upload?

• All images should be in jpeg format. Upload 20-30 pictures of your subject. Preferably cropped or shot to 1:1 aspect ratio.
• We recommend uploading at least 3 photos of full body or entire object + 5 medium shot photos from the chest up + 10 close ups.
  
• Variation is key - Change body pose for every picture, use pictures from different days backgrounds and lighting, and show a variety of expressions and emotions. Make sure you capture the subject's eyes looking in different directions for different images, take one with closed eyes. Every picture of your subject should introduce new info about your subject.
• Whatever you capture will be over-represented, so things you don't want to get associated with your subject should change in every shot. Always pick a new background, even if that means just moving a little bit to shift the background.
• Super important - Pick a good className. Something broad that you could associate your subject with. What works best? We don’t know! Please experiment and share! Some use “man” or “woman”, but we generally get better variations with "person".
When constructing your prompts, always include the keyword to represent the subject.

How do I upload images?

Use our api, check out the docs here
Uploading images is a little harder, but here is a working curl example:
curl http://api.88stacks.com/api/v1/models/ -H "Accept: application/json" -H "Authorization: Bearer TOKEN" -F "name=test" -F 'images[]=@1.png' -F 'images[]=@2.png

Do you support companies?

Yes, we are working with a large group of customers now to deploy models at scale.

API - I would like to use your API for my service or app, would you be able to handle the load?

Currently, we are already providing some big applications and should be able to serve a significant amount more. If you think your service will generate more than 500 models a day, please contact support to coordinate gradual rollout.

How do I do api pagination?

Here is an example:

      url = "https://api.88stacks.com/api/v1/invokes?&page=1"
      urls = []
      loop do
        response = HTTP.auth("Bearer #{token}").get(url)
        headers = response.headers

        link_header = headers["Link"]
        break if !link_header || !link_header.include?("rel=\"next\"")

        next_link = link_header.split(", ").find { |link| link.include?("rel=\"next\"") }
        url = next_link.split(";").first[1..-2]
        j = JSON.parse(response)
        j.each do |jj|
          urls << jj.with_indifferent_access
        end
      end

I have more questions, how can I contact you?

support@88stacks.com