T5-XXL

2 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement Jan 4, 2025 by comfyanonymous (Comfy) · said 4 times in 1 episodes since 2025 · across every show →

Mentions by year

brought up most by comfyanonymous (Comfy) (4)

tap a year for its mentions
0021412025episodesmentions
0112025episodes it came up in
0020.5412025episodesmentions per episode
2025 4 mentions in 1 episode

every mention, scene by scene, with the transcript →

Everything said about T5-XXL, oldest first

Jan 4, 2025 neutral
Assertion Supported
Comfy: Prompt weighting does not work on deep text encoders like T5-XXL
“This stops working the deeper your text encoder is. So, on T-Five XSL, it doesn't work at all, so.”
comfyanonymous (Comfy) Jan 4, 2025 ▶ 23:06 AI Engineering for Art - with comfyanonymous
Jan 4, 2025 positive
Disclosure
Comfyanonymous: Stability AI internally trained effective T5-XXL textual inversions
“Back as like when I was at stability, we actually did train internally some, Like textual versions on like T five XXL actually worked pretty well, but for some reason, yeah, people don't use them.”
comfyanonymous (Comfy) Jan 4, 2025 ▶ 18:49 AI Engineering for Art - with comfyanonymous
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.