Evidence receipt / evaluation
Published · transcript-backedComfyanonymous: evaluation
4 Jan 2025 Latent Space AI Engineering for Art — with comfyanonymous, of ComfyUI
“Like if, if someone gives a huge prompt, they expect at least some of the concepts at the end to be like present in the image. But usually when they give long prompts, they, they don't, they like, they don't expect like detail, I think.”
Source trail
Everything needed to verify it.
- Speaker
- Comfyanonymous
- Attribution
- Verified speaker
- Claim type
- evaluation
- Recorded
- 4 Jan 2025
- Publisher
- Latent Space
Transcript context
…Like the positioning of the words really, really matters then, right? Like this is why order matters in prompts. Yeah. Yeah. Like it, it works, but it's, it's not ideal, but it's what people expect. Like if, if someone gives a huge prompt, they expect at least some of the concepts at the end to be like present in the image. But usually when they give long prompts, they, they don't, they like, they don't expect like detail, I think. So that's why it works very well. And while we're on this topic, prompts waiting, negative comments. Negative prompting all, all sort of similar part of this layer of the stack. Yeah.…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.