Thanks to our sponsor Abacus AI. Try their new ChatLLM platform here: chatllm.abacus.ai/?token=aisearch
@LouisGedoАй бұрын
👋
@BlakeEMАй бұрын
Am I the only one that noticed that CalicoMix is not SDXL? If only we had an AI assistant to double check these things!
@lanzer22Ай бұрын
The funniest thing about SDXL is that a My Little Pony model had become the gold standard for anime generation and hence forth most anime XL models are based on Pony XL
@KibitoAkuyaАй бұрын
OH, so that's what they mean when they say pony based
@hipjoeroflmto4764Ай бұрын
Makes sense those mlp characters have giant anime eyes
@hipjoeroflmto4764Ай бұрын
So it should be good at gmod images too then
@lanzer22Ай бұрын
@@hipjoeroflmto4764 The author did a diligent job in training pretty much all the popular anime characters and did a great job in tagging the training data correctly, and as a result you can give keywords to numerous character references, styles and emotions and get great results out of the box.
@oat1000Ай бұрын
@@hipjoeroflmto4764 its because the person that made the model has a good training dataset, nothing to do with eye size
@maickelvieiraАй бұрын
Ir is crazy how this just came out of the box with so much potential, really wanna see what this will be in some time.
@theAIsearchАй бұрын
yep, looking forward to what the open source community can build from this
@handlenumber707Ай бұрын
@@theAIsearch Just tried it. The first attempt, despite telling it not to put random figures in the background or create mutant hands, or multiple limbs, did just that. The second attempt surprisingly obeyed some commands, but did the same, as did the third attempt. It's just dumb.
@kamillatochaАй бұрын
a new KING .. cant do NSFW .........
@thegameboyshowАй бұрын
until... you make it
@theAIsearchАй бұрын
😭
@Doctor_Sex_0Ай бұрын
Breh
@silvermushroom-gamifyevery6430Ай бұрын
> open source image gen > cant do NSFW The universe is morphing itself to make this statement false as we speak
@armondtanzАй бұрын
I'm sick of censorship. I couldnt even do a hostage scene in luma, it kept knocking it back. Just ridiculous if your into horror stuff of wanna create a horror/thriller trailer.
@amitnishad0777Ай бұрын
Following you since months Love your work Thanks for keeping us updated about the latest AI technology
@theAIsearchАй бұрын
Much appreciated!
@RedSpiritVRАй бұрын
SDXL is king because it's unfiltered It can do things better, to try and filter things in any sense removes its ability's and strengths. Always go unfiltered.
@jtjames79Ай бұрын
I also don't care that much about zero shot. I can break up the composition, do infill and outfill, lighting and background separately. There's a certain minimum number of steps you need to do yourself otherwise it's not really creative. IMHO YMMV.
@hurktangАй бұрын
it's filtered, just less heavily. If you try to make NSFW, you'll be much better off with a custom model based on SD 1.5
@mirek190Ай бұрын
Finally something is happening in the world of picture generation! From more than a year only existed SD and SDXL . Lately we got SD 3 ( lol) , Kolors, AuraFlow.
@bertilorickardspelarАй бұрын
Don't forget Playground
@lukasbeyer2649Ай бұрын
the stable diffusion zebra would totally be something we'd see on an album cover
@gameboardgamesАй бұрын
Right on! As a solo indie game dev, its incredible what I can do with AI tools now versus even just a year ago. Total... game changer.
@handlenumber707Ай бұрын
Just tried it. The first attempt, despite telling it not to put random figures in the background or create mutant hands, or multiple limbs, did just that. The second attempt surprisingly obeyed some commands, but did the same, as did the third attempt. It's just dumb.
@fritt_wastakenАй бұрын
@@handlenumber707skill issue tbh
@losing_interest_in_everythingАй бұрын
Technical artist here. Blender for 3D and vector graphics for 2D. It's straightforward. Relying on AI might actually consume more of your time and effort.
@handlenumber707Ай бұрын
@@losing_interest_in_everything Generative AI is really for dummies. I mean, come on. In order to get anything decent out of it, you have to create the artwork you want first, feed it to the machine, wait for its output, then correct what you get back, paying for your trouble. No decent artist will bite.
@losing_interest_in_everythingАй бұрын
@@handlenumber707 Yes! In my company, I assist HR department when we have to recruit 3D artists, sound designers, and technical artists. Since the rise of AI, my job has become a lot harder. In 2018, I rejected people because their skills didn't fit our needs. Now, I reject people because they have no skills. The worst are the arrogant ones who think they can be our "thinking guys." These candidates make my day better because I get to crush their hopes of being "prompt engineers." This year, I've already rejected around 20 of them, and it was deserved!
@fzigunovАй бұрын
I don't understand why not train the model with the NSFW images and then censor them after generation. Would make for far better models.
@drdca8263Ай бұрын
Less risk of letting some through.
@orthodox_gentlemanАй бұрын
I am a landscape architect and I have been researching the best model to help me! I have found that Midjourney so far is the best for me but after watching your video I am confident in trying SD for landscape design images!
@theAIsearchАй бұрын
Best of luck! SD with controlnet is great for landscape design
@AbubakarMunir712Ай бұрын
12:00 The way it separated coconut and drink is quite funny😂
@FluffRatАй бұрын
High prompt adherence and NSFW restriction are mutually exclusive. The more precisely you can steer the model the easier it is to drive around their speedbumps.
@cmdr_talikarniАй бұрын
In my testing, I've found most of them don't work well with natural human language. They won't understand wording like "next to it" or "by its side". The AI processor reads "next to it" and just places the coconut and/or drink next to whatever, maybe the tree, maybe the water, maybe the plant to the side. The generation doesn't recognize "it" as being associated with anything like the human brain would. Sometimes it may just get it right by chance, other times like the SDXL and SD3 it sees "coconut" and "drink" separately, randomizes the placement of the item. Using comma delimited with direct wording I found is still the best method, even with new tools. Don't use alternate descriptors like "there", "it", or similar wording, and don't use negatives like "no item" in the positive prompt. Polar bear wearing Hawaiian shirt, wearing sunglasses, sitting in hammock tied between palm trees, beach scene, coconut drink with red umbrella on ground
@theAIsearchАй бұрын
Interesting, thanks for sharing!
@cekuhnenАй бұрын
Yeah that is very true - very quickly run into those models not doing what I plan to do besides all the hype. AI should really be more pro programmed logic - it is not more.
@juschu85Ай бұрын
Even if you don't even plan to generate NSFW pictures, it likes like you have to wait for user-trained versions of AuraFlow and SD3 if you want to generate something that involves some form of human limbs.
@gRosh08Ай бұрын
Cool. Waiting for the beginners tutorial.
@Margen67Ай бұрын
birb
@luisbriceno5242Ай бұрын
If it is open source, then I hope the comunnity would be able to finetune unlike SD 3.
@theAIsearchАй бұрын
im expecting a ton of fine tuned models for auraflow to come out soon!
@generalawareness101Ай бұрын
None of these are worth a damn until we can train them locally. That is when the magic happens.
@user-qn6kb7gr1dАй бұрын
Generation uses a tiny fraction of compute needed for training. You wouldn't live long enough to train anything decent in this domain on your home pc.
@generalawareness101Ай бұрын
@@user-qn6kb7gr1d Then it is a dead mofo.
@eSKAone-Ай бұрын
SDXL baby!
@theAIsearchАй бұрын
+1
@_dragoАй бұрын
+1
@elseifforwhileАй бұрын
Link 🔗 please
@ImdrekaiserАй бұрын
So hype for a new competitor in the field
@theAIsearchАй бұрын
finally!
@handlenumber707Ай бұрын
Just tried it. The first attempt, despite telling it not to put random figures in the background or create mutant hands, or multiple limbs, did just that. The second attempt surprisingly obeyed some commands, but did the same, as did the third attempt. It's just dumb.
@fritt_wastakenАй бұрын
skill issue
@handlenumber707Ай бұрын
@@fritt_wastaken It's like some con artist trying to con an actual artist to pay to hand over his work. It might work on a child, perhaps, maybe.
@joelrobinson5457Ай бұрын
@@handlenumber707these channels don't want bad or realistic feedback, they just want quick positive build up, don't trust them for anything reliable.
@handlenumber707Ай бұрын
@@joelrobinson5457 I trust NO KZbin channel. They exist be corrected only.
@Dave-rd6spАй бұрын
It's still very early in its training, thus the 0.1. Given that it's a 6.8B param model, almost triple SD3, fine tuning should be a beast.
@moopindomoop7442Ай бұрын
Thanks for your video. I watched just couple of minutes but when the day comes, and I need a picture of zebra playing Ice piano on the hilltop, I will definitely watch the rest…
@AnonymousFloofАй бұрын
OMG! This Ai takes the cake for me for one reason.. I asked it to generate a centaur and it delivered first try, TWICE! and with all features I asked for! Do you realize just how crazy this is? if not, ask any other AI image generator the same thing. I dare you lol
@theAIsearchАй бұрын
yes, this one is great for prompt following
@handlenumber707Ай бұрын
Just tried it. The first attempt, despite telling it not to put random figures in the background or create mutant hands, or multiple limbs, did just that. The second attempt surprisingly obeyed some commands, but did the same, as did the third attempt. It's just dumb. EDIT: There's no negative prompt box. Doesn't really matter as I removed those instructions and it still failed.
@drdca8263Ай бұрын
@@handlenumber707When you say you told it to not include those things, do you mean like in a “negative prompt” field, or that you put like, “no [thing you don’t want]” in the prompt ?
@handlenumber707Ай бұрын
@@drdca8263 There's no negative prompt box. Doesn't really matter as I removed those instructions and it still failed.
@fritt_wastakenАй бұрын
Pony diffusion makes centaurs just fine. Ask my Lillia folder ..What?
@stephaneduhamel7706Ай бұрын
25:30 CalicoMix is a SD1.5 finetune, not SDXL. Wich is even more embarassing for SD3 and AuraFlow.
@KillbackJobАй бұрын
I swear to God this is the best AI channel. Peace be upon you, good sir
@theAIsearchАй бұрын
Thanks!
@rawkehАй бұрын
So, AuraFlow for initial generation, SDXL for refining
@victk64Ай бұрын
this thing can't generate a simple image of an EMPTY room! SD 2.1 can do this easily...
@b3arwithm3Ай бұрын
In your opinion, what is the good ones for generating scenes with multiple characters consistently? I find that most struggle with comprehension even for a single character. They focus too much on rendering quality and it takes hundreds of attempts and tweaking to produce the right content in the picture. Most of time we achieve it by luck and it is hardly reproducible.
@loth4015Ай бұрын
I tested it and it's not that great. It didn't follow my prompt at all. All others I tested follow my prompt.
@theAIsearchАй бұрын
do you mind sharing the prompt? i find that for simple prompts sdxl does a much better job. aura excels in understanding very complex prompts like the ones i demoed
@JonnyCrackersАй бұрын
It's not that good currently, but I'm glad to see another open source model come out.
@Muz889Ай бұрын
I hope someone makes something like Fooocus for Aura flow.
@deeceehawkАй бұрын
Thank you so much for your fantastic review comparison! I was wondering about this new model, and obviously it looks pretty fantastic when it comes to following the prompt! I have been trying to do cartoons style stories, and this will obviously help tremendously! Thanks again :-)
@theAIsearchАй бұрын
You're welcome, and thanks for sharing!
@TheMadSquАй бұрын
Great video and model. THX for sharing. The most important information comes at about 20 min in the video btw :D
@theAIsearchАй бұрын
Thanks for watching!
@NakedSageAstrologyАй бұрын
All good except one point. Does a Zebra have White Stripes, or Black Stripes? Why?
@theAIsearchАй бұрын
😵💫
@fritt_wastakenАй бұрын
The answer is black stripes if I remember correctly. There is a rare genetic anomaly in zebras that removes the formation of their stripes, which makes them white
@quercus3290Ай бұрын
dazzle camo
@JustFor-dq5wcАй бұрын
Zebra is black with white stripes. Why? Evolution. To be precise camouflage, thermoregulation, and some other things.
@IquryАй бұрын
I feel like SD just focused on realism while AuraFlow on accuracy
@twindenisАй бұрын
Dont forget that SD with likely SD3(?) is going to have a non so open source friendly structure, so may as well test dalle-3 too.
@AxacqkАй бұрын
Why didn't you try higher guidance setting with the zebra?
@user-zs8lp3lg3jАй бұрын
I am here to study cognition. I need to elicit fascination from a compelling subject.
@TheSchwarzKaterАй бұрын
I wonder how we can get the gear going for AuraFlow. I have so much SDXL (Pony actually) Lora saved, the switch will be hard. I'll personally will follow the lead of the NSFW creators ;)
@theAIsearchАй бұрын
pony is awesome! it's a shame that auraflow is censored
@christopherneufelt8971Ай бұрын
I tried the image, Portrait of Darth Vader enjoying some cocktails with girls in bikini on a beach. It is not bad, but at least we have some glimpses of the guy having some time away from the Emperor. Nice.
Ай бұрын
Playground 2.5 should be a better alternative, with good anatomy images.
@hurktangАй бұрын
SD 1.5 is superior still, if what you want to do in NSFW. SDXL was LESS censored, and therefore it understand basic anatomy. But not to the point where it could fool anyone. Custom models made from SD 1.5 are much better at this still.
@IMR.ProjectАй бұрын
love it
@StefanReichАй бұрын
That was great
@theAIsearchАй бұрын
thanks
@BlakeEMАй бұрын
You used SDXL-Lightning based fine tuned model, but it follows prompts less than the base SDXL at higher steps/CFG scale. You are also using a fine tuned model, that is not as creative as the base SDXL model, due to overfitting of a limited training data set. CalicoMix is SD1.5 and not SDXL, as it states in this video. Is AuraFlow based on the SDXL architecture (like Pony Diffusion)? If so, you may want to use the specific SDXL text encoder nodes so you get the best coherency at the edges when generating different aspect ratios. So far, I haven't been very impressed by these models trained on very limited data sets. They lack creativity, because the data is so limited. They ignore words that are not in the training and negative prompts don't work as well, because they don't put the things you don't want in the training images.
@sevenseven31Ай бұрын
is there more sources to convert images to text is very helpful
@HysorixАй бұрын
the model is really good for alpha but its generations seem like stacked images someone would cuttout and make in photoshop and it cant do nsfw meaning slightly exposed skin like legs or arms breaks anatomy
@SS801.Ай бұрын
looks promising good video
@theAIsearchАй бұрын
thanks!
@MrInterpriserАй бұрын
Do you know about AI that describes what it sees in the footage?
@MoukreaАй бұрын
Refined models tend to not follow prompts as well as their source models, hence the prompt not being that much followed with RealVisXL as it's one of the realistic ones which are less "creative"
@thirien59Ай бұрын
with midjourney, you dont get failed human bodies and wrong styles. it seems to me opensource is clearly lagging far too behind proprietary models, unlike chatbots where llama3 works correctly
@faintentАй бұрын
this guy is Fireship on god
@gauravsharma-bt2mtАй бұрын
Hi anything you suggest for for lip sync ai tool open-source, my use case is i have a video in english i want to convert it into hindi lipsync
@PMXАй бұрын
You were using 50 steps for the first couple of images but only 28 after you switched to hf, that may have made images less detailed
@KDawg5000Ай бұрын
So the lesson I got is; use Auraflow to create an image that actually follows your prompt. Then use that image as a controlnet in SDXL to make a realistic image from it. 😁
@nicktumiАй бұрын
Do you have an example of that workflow?
@theAIsearchАй бұрын
awesome idea!
@hipjoeroflmto4764Ай бұрын
@@nicktumi he just said the workflow lol, if u didn't notice I think you got other things to worry about
@nicktumiАй бұрын
@@KDawg5000 duo you have a error for comfyui for this example?
@nicktumiАй бұрын
@@hipjoeroflmto4764 y r u gA
@hognetitlestad382Ай бұрын
16GB? No smaller version?
@usmankhan-xi4dlАй бұрын
Why does zebra don't have a tail yet😂?
@igiveupfineАй бұрын
oh. in the SDXL base model they did/do still have NSFW images/things in the base model? where as any SD AI models after that do not? interesting. a shame that removing them made it so much worse at understanding people.
@RunnerProductionsАй бұрын
So if you didnt use comfy ui , it would just be hard to run this right? like you would need to clone more of the code on github and run it through VS code ..?
@theAIsearchАй бұрын
correct, the only way that was mentioned in their blog was comfyui. you could try duplicating and tweaking one of the online spaces
@EnergyswordsundayАй бұрын
It's comical we use anime thumbnails than ai ones
@user-kb1su7mg1gАй бұрын
just started watching. i dont know it looks bad to me
@merce414Ай бұрын
Thank you!!!
@theAIsearchАй бұрын
You're welcome!
@RIUUI007Ай бұрын
I use midjourney, how does midjourney stack up to this? Is midjourney outdated now or considered low end?
@Astro-uv1xqАй бұрын
It's still considered to be the best/easiest to use, I believe
@JonnyCrackersАй бұрын
Midjourney blows this out of the water easily.
@theAIsearchАй бұрын
mj is great but it's closed & paid. i'm only comparing open source here
@fritt_wastakenАй бұрын
@@Astro-uv1xq Midjourney was never better than SD. Easier to use, yes. But not really useful
@quercus3290Ай бұрын
@@fritt_wastaken hmmm dunno dude, midjourney can make insanely high quality images if your good at prompting with it. A good number or loras pretty much use MJ images for training data.
@Ai-Art-42Ай бұрын
good video
@planethanzАй бұрын
This will not replace SD 1.5. or SDXL) because it's heavily censored. So it may replace SD 3 (which is also terrible - I guess censorship requires more resources than progress in companies like this)
@theAIsearchАй бұрын
thanks for sharing. agree that censorship is a major limitation here
@planethanzАй бұрын
@@theAIsearch But what could be a use case: Using this new model just for prompt understanding and as a base for img2img workflows. I've also achieved great results with MJ base images and img2img (or img2vid) workflows in comfyUI using those images as part(!) of the input.
@Entity303GBАй бұрын
I say the next vid is about llama 3.1 and a lot about 405b
@fulldivemediaАй бұрын
thanks
@TAGSlaysАй бұрын
"A Very Tricky Font" or just a poorly written one? I agree, Auraflow is much better at creating images from shitty prompts. You literally do not tell the AI that you want the hammock tied to the two trees and then complain about it.
@jeremys1977Ай бұрын
Great channel. Ive been following since the start. AuroFlow looks promising, but no way will it take on SD. In order for these image gens to be really reliable on a professional level, they will need to integrate tools to modify iteratively. You can't truly work on prompts alone.
@theAIsearchАй бұрын
Thanks for sharing!
@twisterrjlАй бұрын
AROUND A WEEK AGO WEEK AGO
@macowayeuАй бұрын
Replace Stable Diffusion ? 😮
@igorthelightАй бұрын
Only for some cases
@nickjones1609Ай бұрын
stable cascade base model is better than sd3 and sdxl base model, probably should've used that instead
@rownakislam6404Ай бұрын
Can foocus ai platform use sdxl? Is there a open source for sdxl?
@sherpyaАй бұрын
almost every existing software does support sdxl
@thedevo01Ай бұрын
WELL ACKSHULLY 😂 have you seen baby zebras that are black with white spots? Yeah, zebras are black with white stripes, so technically, SD3 got it right 😂
@HervooАй бұрын
Still no nsfw
@theAIsearchАй бұрын
😢
@ryzikxАй бұрын
its a safetensor file, wonder if i can just plug it into my comfyui folder and use it from there?
@igorthelightАй бұрын
Try that! ;-)
@hurktangАй бұрын
No "safetensor" is a file format, it have nothing to do with the training data. SD 1.5 is actually the best still for anatomy.
@keenheat3335Ай бұрын
i guess you still need controlNet and sdxl.
@Sujal-ow7cjАй бұрын
I don't think it is that good if sd3 was uncensored and with fine tuning will crush all of them 😢
@SP4595-gs7zwАй бұрын
May be someone can try fine-tuning it for NSFW task?
@nomad_apeАй бұрын
Hello anyone knows an AI that can generate 2D spritesheet like spritesheet to animate a horse walking or a bird flying? I need it for make simple game. Thanks in advance 🙏🙏
@voltageconcepts3807Ай бұрын
The king has no clothes lol
@theAIsearchАй бұрын
😏
@drendelousАй бұрын
is abacus good?
@PatronGamingАй бұрын
following you from alot of months, just want to let you know you are a fkin GOAT in AI teaching.
@AIChameleonMusicАй бұрын
It makes poor images of tuxedo mask compared to others I use.
@reezlawАй бұрын
SD3 often looks like the worst of both worlds, I don't see the point of this model
@theAIsearchАй бұрын
true
@HenkvanAlphenАй бұрын
Sdxl’s yoga pose wasn’t perfect the woman’s foot is flipped 😂
@quercus3290Ай бұрын
training on synthetic data is sketchy at best.
@Badboy-zo7ofАй бұрын
copilot ai is the best
@Brain4BrainАй бұрын
It run on DALL-e 3 💀
@user-pc7ef5sb6xАй бұрын
Sorry bro, SDXL is still king
@theAIsearchАй бұрын
yep, that's my preferred model for now
@MilenninАй бұрын
With how bad these models are at anatomy, what point is there in using them? Legit question. What do people use these image generators for when they can't properly generate a human body.
@handlenumber707Ай бұрын
They're cheap, and people who can't draw think bad drawings look good. For one off images, pinups, celebrities and general throwaway artwork. the undemanding will find this useful. For actual artisans it's a source of mirth. Just tried it. The first attempt, despite telling it not to put random figures in the background or create mutant hands, or multiple limbs, did just that. The second attempt surprisingly obeyed some commands, but did the same, as did the third attempt. It's just dumb.
@user-fl3mk5kn8oАй бұрын
Ideogram wins by a longshot
@DigitalDripUKАй бұрын
EARLY GANG
@theAIsearchАй бұрын
😃
@Gabriel.Ponce.De.Leon.777Ай бұрын
Why girl punches man?
@TonyThaiАй бұрын
she has androphobia
@kanall103Ай бұрын
one more
@carleyprice3138Ай бұрын
i really enjoy your content, i can't wait to hear what you have in store for us about Flux :D
@theAIsearchАй бұрын
Thanks! Coming soon!
@juschu85Ай бұрын
2:12 Uhm, no. Just no! There is definitely not an infinite number of different images for one prompt. That's just not how math works. You'll never have infinite possibilities for a finite set of bits. For n bits, there are 2^n possibilities. You would need infinite resolution or infinite color depth for infinite possibilities. Please don't use the word infinite like that when you said "in theory" before, which kind of gives it all a scientific flavor.
@user-qn6kb7gr1dАй бұрын
It's fine. Seed in theory can be from 0 to infinity. Some generations would not be unique and that's it.
@sadshed458527 күн бұрын
and now we have flux
@theAIsearch27 күн бұрын
yep. bye auraflow
@1conscience0dimensionАй бұрын
Welhome
@panzerofthelake4460Ай бұрын
it's not better, it's not a king it's nothing different, just a different dataset