News for hackers. Stuff that matters.

A comment on The open weight Flux text to image model is next level. Parent comment

Re:The open weight Flux text to image model is next level by lukan on Thursday August 01, 2024 @11:56PM (#41135973)
"Recently Claude began to allow generation of SVG drawings, and asking it to draw a unicorn and later add extra tails or horns worked correctly."

That sounds interesting! Were the results somewhat clean and clear SVG or rather a mess that just looked decent?

[ Parent | on HN ]
Re:The open weight Flux text to image model is next level by TheAceOfHearts on Friday August 02, 2024 @12:30AM (#41136114)
Here's the screenshot [0] that was shared with me. It's obviously pretty basic, but Claude understood the correct location for where the horns and tails should be located. This looks like a clear iterative improvement over older models.

[0] https://imgur.com/Cc5uJNg

[ Parent | on HN ]