I experienced the same. I looked at marginal distributions, correlations between OHLC and correlations across time. They were all similar to real data. In addition to that, I looked at characteristic that are present in specific markets such as fat tails, volatility clustering, and leverage effect. The synthetic data generated by GANs showed these as well. TimeGAN is a good model, but lags a bit in the latter.
Have you ever looked at GARCH? It is really good in predicting future volatility/variance, and the packages in R and python are really easy to use. https://en.wikipedia.org/wiki/Autoregressive_conditional_heteroskedasticity
Well then if you want to proclaim impressive results make them spendable profits. Many do research all the time.