“Rio 3.5 Open 397B is a frontier-class general-purpose AI model developed by IplanRIO, the municipal IT company of Rio de Janeiro's city government. Post-trained from Qwen 3.5 397B…”
Hi, as someone interested in both ML and fashion, this is pretty cool!
How are you addressing the idiosyncrasies of how clothing can fit differently? Personally, I like wearing a variety of different fits (slim/boxy/etc).
From your demo, it seems like the model is learning a single type of fit (the average of your training data?) and then mapping a texture + details onto this single fit.
In physical reality, the fit of a garment is obviously affected by both body type and garment measurements (as alluded to in other comments). Data quality (e.g., consistent scale and angle) also would be important. I imagine that because of these factors, the fit estimation problem is very challenging.
I had a sort of similar incident happen with the youtuber Siraj Raval who was ripping off people's original projects (without attribution) and making videos about them -- and spun a career out of it.
It took many attempts to get him to attribute my project (in accordance with its license) although he was caught repeating this type of behavior later on.