Hyper-SD - Better than SD Turbo & LCM?

The new Hyper-SD models are FREE and there are THREE ComfyUI workflows to play with! Use the amazing 1-step unet, or speed up existing models by using the LoRAs.
Better than LCM? Take a look for yourself and see!
Want to support the channel?
/ nerdyrodent
Links:
huggingface.co/ByteDance/Hype...
== More Stable Diffusion Stuff! ==
* Installing Anaconda for MS Windows Beginners - • Anaconda - Python Inst...
* Installing ComfyUI for Beginners - • How to Install ComfyUI...
* ComfyUI Workflows for Beginners - • ComfyUI Workflow Creat...
* Faster Stable Diffusions with the LCM LoRA - • LCM LoRA = Speedy Stab...
* Make an Animated, Talking Avatar - • Create your own animat...
* Make A Consistent Character in ANY pose - • Reposer = Consistent S...

[@handsomejack672]

Works in forge and A1111 alongside controlnet ip adapter face id, tested it in 4 steps SD 1.5

[@JustFeral]

That fucking outro sound lol

[@NerdyRodent]

😉

[@MarcoCholo-iz9js]

Los fucking canguros

[@Tinnur_]

Hyper-SD works well with Krita live generation. 60 rodents per minute. Thank you for sharing!

[@NerdyRodent]

Nice 👍🏽

[@jibberishballr]

Thanks for this! Outro song is bomb and you're always great content. I love the ability to quickly generate decent images on one pass. Suggestion: it would be interesting to see a "low vram" e.g. 6GB workflow taking the 1 step generations with this model and then working those into more detailed images.

[@MrSporf]

Nerdy really is the geezer! Cheers, mate

[@NerdyRodent]

😉

[@Jeremy-sk9qh]

does it work with automatic 1111?

[@superdrew907]

ROFL, is it just me or is that outro song worth the price of admission all by itself?! I wouldn't be surprised if people started tuning in regardless of what the future videos will be about, just to check out the new outro. . Keep up the excellent work Nerdy, u crushin it my man...err crushin it, my Furry Nerdy Friend!

[@NerdyRodent]

😉

[@slashkeyAI]

Thank you sir.

[@NerdyRodent]

Most welcome!

[@tribuzeus]

Hi. Could you recommend a good video enhancer? Thanks

[@icedzinnia]

thank you, sir.

[@NerdyRodent]

Most welcome!

[@Duckers_McQuack]

Hoi, do you know if comfy and webui forge can do multi model locations? as i tend to model hop a bit, and got such a collection now that i split them to each their drive. One for SD 1.5 and one for SDXL. Is there a easy way/launch command to use multiple drives for model storage?

[@NerdyRodent]

Symlinks can work wonders for any app 😉

[@user-oz9tf9zp7k]

Could you not do something like, full strength lora on step 1, and then with the lora off on steps 2-4, and get 100% quality?

[@articraftic]

what's the different of lightning and hyper sd?

[@yahiiia9269]

Can you make a video about HiDiffusion?

[@WhatsThisStickyStuff]

Its not out yet for any UI but as soon as it is I also want to see this. Im keeping an eye out and hoping it gets released soon

[@peacetoall1858]

I wonder how this would perform on a measely 4GB VRAM system like mine

[@voxyloids8723]

How to make it run faster ? I want to use with canny CN and webcam image in RT )) I mean I have the same speed 1or 2 fps in sec on 3090

[@mattelder1971]

Can this be used with Forge as well, or is it only working with ComfyUI?

[@handsomejack672]

works on Forge and A1111

[@voxyloids8723]

Do you compare fp16 is faster ?

[@ady-001]

The 8 step XL lora works well in A1111, but you need to play with the weight 0.8-1 and Sampling method

[@dreamzdziner8484]

Thanks. Yes the 8 Step Sdxl one seems to work pretty okay with Sd Forge also. But nothing else.

[@forfreeiran8749]

​@@dreamzdziner8484there is a new lighting model, 3 steps! It works well in forge too CreaPrompt_Lightning_Hyper-SDXL

[@jonmichaelgalindo]

Couldn't get it running in A1111. :-(

[@Lucas-uk6fj]

May I ask the author, where can I download the workflow demonstrated in your video? Thanks

[@NerdyRodent]

You can get my modified workflows from www.patreon.com/NerdyRodent

[@_l3m35_]

I tried it for a little bit with A1111, the 8steps can be really useful but it's quite limited on sampling methods -- DDIM works good, others may vary and a few will simply destroy the result. Tried the 1step and it was a mess.

[@NerdyRodent]

Yup, ddim sgm uniform is the best

[@Your-Stranger]

1111webUIで使えますか？？

[@marjolein_pas]

Great, superfast with IPadapter!

[@steve_jabz]

What's it like vs lightning?

[@NerdyRodent]

Better 😉

[@steve_jabz]

They compared it with 1 step, but even though it didn't follow the prompt well, it still looked the best aesthetically, and usually you would use 4-8 step with lightning and get high quality results fast, plus you kinda showed that 8 step is preferable with hyper-sd anyway. I'll take your word for it though

[@resh6701]

Sooo... Better or not better ?

[@HestoySeghuro]

Additional loras work?

[@NerdyRodent]

Give ‘em a go!

[@_l3m35_]

Yes.

[@ImmacHn]

But does it blend?

[@NerdyRodent]

Almost certainly!

[@twilightfilms9436]

A1111?

[@ady-001]

the 8 step XL lora works well in A1111

[@j_shelby_damnwird]

The closing AI generated song, so very nineties 😅

[@Pauluz_The_Web_Gnome]

Hi, I saw that you choose the Proteus-Rundiffusion model, for SDXL, but they have also a model withoutCLIP...If you run the prompt again, with the same settings, you will get your Rodent Detective! Also (rodent:1.4) works too! 😀 So it's not Proteus, but the version of Proteus. kzbin.info/www/bejne/gnK0io2Nl9KeraM

[@NerdyRodent]

Yup - if you’re not getting the results you expect, try switching models!

[@Pauluz_The_Web_Gnome]

@@NerdyRodent Thanks for your comment, Nerdy!

[@stevehaney344]

It's only available on comfy? Dear God why?!

[@alpaykasal2902]

maybe because it's so super awesome?

[@FutonGama]

with all respect of course

[@SetMeFree]

just bite the bullet and learn it. It's so good.

[@alpaykasal2902]

@@SetMeFree Agreed!

[@pedroserapio8075]

03:56 Trump fish riding a bike!

[@omegablast2002]

quality > speed

[@bankenichi]

Seems interesting, but lightning models already do similar stuff and they are easily compatible with other uis like a1111.

[@NerdyRodent]

Good job this is so much better than lightning!

[@CharlesLijt]

China No.1

[@procrastonationforever5521]

I can't express how much i despise pixel art, despite being one of those who used Spectrum-ZX. Who are those weird ppl that fall for this absurdly outdated way of displaying things while having all this technologies?

[@GumOnTheWall]

realism does not equal better. artistic expression does not care nor strive to be necessarily realistic. other wise all art would try to be as realistic as possible

[@j_shelby_damnwird]

Easy there, It's just modern mosaic art 😊

[@timeTegus]

the udio outrow ẃas epic