Artflow About

About Us


Artflow lets users generate visual content with the help of AI.

We strongly believe in the liberating act of creativity and want to allow anyone to make and share their creations with the world, experiment in a positive environment and express themselves through this novel medium.

As a first step on our road map, our site allows users to generate portraits based on short, textual input. The machine learning system interprets submitted prompts into images.


FAQ


Does it support non-English descriptions?
Only English is supported at the moment.

Can I use the images from Artflow in my project?
Yes, as long as you attribute Artflow. All images are licensed under CC BY. You can find more information in our Terms of Service.

Are you just pulling images from the web, or are those portraits really generated by a machine?
All images on Artflow are generated on the fly, based solely on user input, by a combineation of machine learning models (more specifically, we use Generative Adversarial Networks as well as the CLIP model from OpenAI). We do not use any existing images and the chances of generating an exact copy of an existing image are practically zero.

Why do I have to wait for the image to get generated?
The generative process is computationally expensive and this takes quite a significant time to generate even on the most powerful hardware. We do our best to expand our capabilities, but at times because of high site traffic, the waiting time might get higher than we'd like.

Are all minority groups represented equally?
Our AI model is trained on accessible data that sometimes carries misrepresentations of the real world, which could lead to biased results. We take this issue very seriously and take measures to bring a more balanced experience to people from various backgrounds. In case you are trying to generate a portrait of a specific gender or ethnicity, you will achieve best results by using specific words to describe it.

I wanted to create an image but the resulting portrait is not related to the prompt I provided.
Natural language understanding still remains a challenging task in AI research, we are working on our best to train the AI models to produce ideal results. In case there's a mismatch between the prompt and the generated image, you want to firstly make sure things are spelled correctly, and use longer, more descriptive prompts rather than a single word or a phrase. You might also want to try a few times with the same phrase, or slightly rephrasing your description, to get the desired result. Experiment with your prompts, it's fun!

How come the same prompt generates a different image each time?
Our AI model, just like human artistic expression, is not deterministic. This way we ensure the content is unique and we can better sample the richness of the real world.

Why is my image flagged as inappropriate?
We try to provide the best experience to every user, both people who create content as well as those who want to explore other's creations. We don't want any explicit, racist or hateful content on our site. We try our best to flag them, and prevent them from being viewed by others. Occasionally our system might flag an other wise unoffending phrase. If you think that is the case, please let us know - this will help us improve the system.

I have more questions, how can I contact you?
For free exchange of ideas, sharing your creations or just giving us a virtual high five, welcome to join our discord server. For media, investors or other official inquiries please send a message to info@artflow.me


Terms of Service



By using the Artflow Platform ("Platform"), you are hereby confirming that you have read and agree fully to these terms of service:

All content created on the Platform is licensed under the most accommodating Creative Commons license **CC BY** that allows both commercial and non-commercial use, including derivative work, as long as you attribute Artflow. This does not however cover the right to use someone's likeness for other than editorial use (see below).

In a situation where an image resembles a real individual, the person in question retains full publicity rights to their likeness. They, or their representative can submit a request to take down the image and Artflow will abide to those request regardless of the image creators intentions. Even in a situation where such a request was not submitted, you do not hold the right to use someone's likeness for other than editorial purposes.

By providing content to the Platform you confirm that you are not infringing on any copyright, meaning you either are the copyright owner, the content license allows unattributed derivative work or the content is in public domain.

By using the Platform you agree that Artflow can store and use the provided information including uploaded images, text and other media for the purpose of improving the Platform, promotional and research purposes.

You take full responsibility for both the provided content (including uploaded images, text and other media) as well as generated content that could be considered offensive, obscene, libellous or in any other way violating the law.

If you are a copyright owner or an agent acting on behalf of the copyright owner and suspect that any User Content infringes upon copyrights, submit a notification to legal@artflow.me.

Disclaimer of Warranties.
Artflow Services and the Platform is provided "As is". Artflow does not make any warranty that access to the Platform will be continuous or uninterrupted and our Services will be error free. You use the Platform at your own risk and discretion.