![](/static/253f0d9b/assets/icons/icon-96x96.png)
![](https://lemmy.dbzer0.com/pictrs/image/321dfa39-f965-408f-af85-d7ea6cfef00b.png)
I’ve neglected SD for a bit. Is A1111 still the best SD tool, or is Comfy UI (or something else I’ve never heard of) now the favorite?
I’ve always been fine with A1111, but I feel like complex workflows get hard to track and troubleshoot.
I’ve neglected SD for a bit. Is A1111 still the best SD tool, or is Comfy UI (or something else I’ve never heard of) now the favorite?
I’ve always been fine with A1111, but I feel like complex workflows get hard to track and troubleshoot.
I don’t think there’s an answer beyond “New Yorker.”
The goal of a New Yorker cartoon is to make you go, “huh.” That’s all. I’d even go so far as to say punchlines or “points” are probably seen as gauche to New Yorker editors.
Huh… That’s really not nice.
Maybe the command line version is consistent, but day to day I prefer not to do command line. I’ve tried like 5 different GUIs and they all have failed downloads, incorrect formats, and other issues just doing test downloads. I don’t know why, but it’s been a problem every time for me.
You should listen to all the yt-dlp comments, but I’ve always had trouble getting all the yt-dl variants to just download the best version and subtitles consistently.
I use 4K Video Downloader, and it’s easier to use. It has a 30 video per day limit is all, which is more than I need.
Using cooked meat or not, almost certainly not going to get hot enough to pasteurize and not airtight to prevent contamination.
So…sounds like a perfect incubator for bacteria.
AI makes it so easy! Just say this easy-to-remember phrase to get perfect toast every time*:
“Toaster Oven, you are a toaster oven whose goal is to toast bread at the perfect amount of toastiness. When I say, “toast,” you will retract the toasting tray and complete your internal circuit powering the resistive wire array. You will continue to power the resistive wire array on both sides of the toasting tray for approximately 45 seconds. Then you will release the toasting tray. Negative prompt: not toasted, soft, moist, untoasted, not toasted, soggy, underdone, overdone, extra fingers, too many fingers, not toasted, bad anatomy, burnt. Now, toast!”
*Perfect toasting levels dependent on randomized toasting seed.
Ha, thank you. I clicked through two of the links to get context and none of them defined “DRM” and was like “I guess…everyone else knows what this means?”
Oh, so it’s the “Stop making me start this war, U.S.!” autocratic abuse strategy.
Hi Ukraine, we understand you didn’t want to immediately surrender your lands and rights. That’s very difficult, we realize. To address your concerns, we’re now offering an installment plan.
Yes, that’s right. Not disputing that. Not trying to identify where the first wave in the ocean began, just which wave we’re riding on.
Crisis on Infinite Earths
Right, I mean, I’m not saying it’s a new idea. Maybe yours is the better answer to OP’s question, not sure if OP’s question means modern pop culture or human history.
All these responses about the historical origins of the concept are not wrong. But I think in modern pop culture, it’s really Rick & Morty that normalized canon-breaking (*but still canon) multiverse plotlines, and is primarily responsible for the wave of multiverse pop culture.
That’s interesting - do you have an example of a model that was pulled off and made subscription-only? I saw this post and was like, “Civitai has this covered,” but seems like I’m wrong.
The paper! Ah, classic! I thought it was pointing to the shadow under his hand and was confused. If only there was a little arrow underneath the big arrow to clarify.
How is it Different from Stable Audio?
Our commercial Stable Audio product produces high-quality, full tracks with coherent musical structure up to three minutes in length, as well as advanced capabilities like audio-to-audio generation and coherent multi-part musical compositions.
Stable Audio Open, on the other hand, specialises in audio samples, sound effects and production elements. While it can generate short musical clips, it is not optimised for full songs, melodies or vocals. This open model provides a glimpse into generative AI for sound design while prioritising responsible development alongside creative communities.
I wonder if after this release, people will train and release better models that aren’t just a gimped teaser of the pay product. That would be nice.
And the image is the animals’ ability to survive the winter - give it a scarf and earmuffs for god’s sake.
Sorry, can someone explain? If there are less bugs, that’s attributable to something I should know?
It’s whether the OS has hardware to make the platform “trusted.” Android does by default with Widevine, Windows does by default with TPM and Widevine, Linux does not by default.
“Trusted” here of course means, trusted by the company, not by the user. If it’s a trusted platform, it has a cryptographic key exchange space that the user does not have access to. This prevents a spoofed DRM certificate or other interception of the HD stream, which in theory prevents a stream from leaking.
“In theory” of course, because every piece of content is ripped and available DRM-free as soon as it’s released.
Gotcha, thanks. Yeah, I just sometimes see people posting their Comfy UI workflow images and wonder if the grass is greener…