High Signal Podcasts Evidence ledger
Method
Browse
← Back to evidence

Evidence receipt / preference

Published · transcript-backed

Comfyanonymous: preference

4 Jan 2025 Latent Space AI Engineering for Art — with comfyanonymous, of ComfyUI

“5 a try cause it's, uh, it's different. I won't say it's better. Well, it's better for some like specific use cases.”

— Comfyanonymous

Source trail

Everything needed to verify it.

Speaker
Comfyanonymous
Attribution
Verified speaker
Claim type
preference
Recorded
4 Jan 2025
Publisher
Latent Space

Transcript context

…Can we talk about models a little bit? So stable diffusion, obviously is the most known. I know flux has gotten a lot of traction. Are there any underrated models that people should use more or what's the state of the union? Well, the, the latest, uh, state of the art, at least, yeah, for images there's, uh, yeah, there's flux. There's also SD3.5. SD3.5 is two models. There's a, there's a small one, 2.5B and there's the bigger one, 8B. So it's, it's smaller than flux. So, and it's more, uh, creative in a way, but flux, yeah, flux is the best. People should give SD3. 5 a try cause it's, uh, it's different. I won't say it's better. Well, it's better for some like specific use cases. Right. If you want some to make something more like creative, maybe SD3.5. If you want to make something more consistent and flux is probably better. Do you ever consider supporting the closed source model APIs?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.

Search evidence