📢 Last chance to get 40% OFF my AI Digital Model for Beginners COURSE: aiconomist.gumroad.com/l/ai-model-course
@baheth3elmy163 ай бұрын
Its extremely bad with humans. Very disappointed with it.
@bytesundbuechse3 ай бұрын
I think its useless for humens. Super disappointing
@17th_Colossus3 ай бұрын
SD3 shows why censorship is always a bad thing.
@tails_the_god3 ай бұрын
EXACTLY i been saying how censorship is bad especially for AI
@bladechild24493 ай бұрын
All been downhill since 1.5 SDXL was ok when the custom trained models peaked, but theres been far less support for it LORA wise etc. We really need to just get our hands on the LLM supported prompting models now. I'd love an offline version of whatever ideogram uses but with trained models and customisation
@MajomHus3 ай бұрын
You can always do your own lora if you want a specific thing.
@bigdaddy53033 ай бұрын
Some of the IP adapter face models and instant ID give better results than any Lora I ever created. With a xl turbo model and a good comfy UI workflow you can pump out amazingly realistic "Lora's" in 10 steps and a single photo
@MajomHus3 ай бұрын
@@bigdaddy5303 lora or a well trained checkpoint is always better, but takes days to make
@VGF64-23 ай бұрын
@bigdaddy5303 I would like to see your workflow, I'm very interested. I was trying with IP Adapter recently and was trying to determine whether it is superior to Loras.
@MajomHus3 ай бұрын
@@VGF64-2 a well trained lora will always beat ip adapter for now.
@Bicyclesidewalk3 ай бұрын
Back to playing around with Stable Cascade - which can generate some really great images.
@AI.Absurdity3 ай бұрын
So far in my testing, it does text a lot better.
@taucalm3 ай бұрын
😁
@cipher8933 ай бұрын
Doing text better is literally one of the advertised improvements.
@amitjangra64543 ай бұрын
I was downloading it with high expectations
@Aiconomist3 ай бұрын
Sorry for ruining it! 😅
@VGF64-23 ай бұрын
Looks like PixArt is the future.
@GumOnTheWall3 ай бұрын
I'm thinking that Stable Cascade might take over
@gu98383 ай бұрын
yeah its so so......at least the base model i think xl lighting is best for now
@styrke92723 ай бұрын
SD 2.0 all over again ?
@duskairable3 ай бұрын
yup DOA
@AltimaNEO3 ай бұрын
Is say worse. At least 2,0 could do some anatomy and coherent scenes .This one fails so bad at everything
@styrke92723 ай бұрын
Sadge
@blacksage813 ай бұрын
Oof, good thing I'm set with my XL Models
@soucravn3 ай бұрын
mate you sure you got a 3060? It took 11 secs for me on the same sample workflow
@memerhuwhite3 ай бұрын
Thanks for the video, Brother! Good to meet another IDM user too 🤣😎👊🏻
@GustavBoye-cs9vz3 ай бұрын
Something feels weird about a company that trained in millions on artists work without consent talk about their license and terms of use. - Don't get me wrong I'm not some sort of anti-ai warrior that writes "AI sucks" on every AI image. - But to see them try to enforce copyright on users when they themselves cared little about it is a bit funny. - I think at some point there will be a complete open source version of some of these models.
@GustavBoye-cs9vz3 ай бұрын
Also impressive work they did, but at the same time not. The newest discoveries in the field is thanks to AI scientists. The dataset is thanks to unappreciated artists. All they really did was just throw a ton of money and compute at it. Which basically anyone could do in theory. And all that compute will be a waste once a smarter architecture or training method is discovered.
@paoloadam3 ай бұрын
I am still hopeful -- SDXL also failed to impress at first and took a while to mature, and this is just a preview not the final product. I am almost finished downloading, I'm very curious to see whst are supposed to he its main advantages, text rendering & most importantly a significantly greater capacity to understand prompts and thus deliver the right image.
@mjkht3 ай бұрын
what is about HunyuanDiT?
@wonder1113 ай бұрын
Not impressed either, though once they are properly plugged into existing quality SDXL workflows, I expect my opinion will change. As raw testing models, I found it rather literal.
@StefanReich3 ай бұрын
Are you using an AI voice? I really prefer actual humans
@user-ld8sy9xu2v3 ай бұрын
Yeah but what if a guy cant speak a good english,TTS voice with clear pronouncing is always better then person with strong accent and when you have hard time to listen what he/she actually said. And TTS is not that bad at all.
@WNTrombone3 ай бұрын
That’s unfortunate especially after all the hype they built around it…
@taucalm3 ай бұрын
I would give it time for year to end, it was released like today so it cant be finetuned yet neither community driven.. sdxl has been around at least 6mo and I guess it was not as good as it is today when it was released..
@Cara.3143 ай бұрын
Except nobody can fine tune it cause of the licensing.
@squirrelhallowino293 ай бұрын
XL was released a year ago. However this SD3 is not the full model, but it's not looking promising. Plus no increase on resolution which is a big limitation right now of any model.
@taucalm3 ай бұрын
@@Cara.314 well that makes it pretty much unusable, it should be opensource to achieve same results as sdxl.
@Jeremy-sk9qh3 ай бұрын
you downloaded the text encoders not the model
@Cara.3143 ай бұрын
Incorrect. They downloaded and explained both clip and unet models.
@xt-cj7jg3 ай бұрын
its bad with humans but good at everything else, if you want strictly human just use another model.