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
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
@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.
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.
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.
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..
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.
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.
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.
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.
📢 Last chance to get 40% OFF my AI Digital Model for Beginners COURSE: aiconomist.gumroad.com/l/ai-model-course
Its extremely bad with humans. Very disappointed with it.
I think its useless for humens. Super disappointing
SD3 shows why censorship is always a bad thing.
EXACTLY i been saying how censorship is bad especially for AI
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
You can always do your own lora if you want a specific thing.
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
@@bigdaddy5303 lora or a well trained checkpoint is always better, but takes days to make
@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.
@@VGF64-2 a well trained lora will always beat ip adapter for now.
I was downloading it with high expectations
Sorry for ruining it! 😅
Back to playing around with Stable Cascade - which can generate some really great images.
So far in my testing, it does text a lot better.
😁
Doing text better is literally one of the advertised improvements.
mate you sure you got a 3060? It took 11 secs for me on the same sample workflow
yeah its so so......at least the base model i think xl lighting is best for now
Looks like PixArt is the future.
I'm thinking that Stable Cascade might take over
what is about HunyuanDiT?
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.
SD 2.0 all over again ?
yup
DOA
Is say worse. At least 2,0 could do some anatomy and coherent scenes .This one fails so bad at everything
Sadge
Oof, good thing I'm set with my XL Models
Thanks for the video, Brother! Good to meet another IDM user too 🤣😎👊🏻
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.
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..
Except nobody can fine tune it cause of the licensing.
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.
@@Cara.314 well that makes it pretty much unusable, it should be opensource to achieve same results as sdxl.
you downloaded the text encoders not the model
Incorrect. They downloaded and explained both clip and unet models.
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.
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.
That’s unfortunate especially after all the hype they built around it…
Are you using an AI voice? I really prefer actual humans
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.
its bad with humans but good at everything else, if you want strictly human just use another model.
It's so bad. I'm pretty disappointed with it.
Ideogram is still better than this