RIP Midjourney? Open Source & FREE AI Art is About to Take Over! DIRECT COMPARISON
Vložit
- čas přidán 26. 06. 2023
- SDXL 0.9 is the latest version of the Stable Diffusion text-to-image suite of models developed by Stability AI, a London-based artificial intelligence startup. It was announced on June 22, 2023 and claims to produce more realistic and detailed images than its predecessor, SDXL beta. It has a parameter count of 6.6 billion and uses two CLIP models to process text prompts and generate images at a resolution of 1024x1024. It also offers functionalities such as image-to-image prompting, inpainting, and outpainting. The model is currently available through ClipDrop, with an API release coming soon, and an open release planned for mid-July
▼ Link(s) From Today’s Video:
✩ Blog Post: stability.ai/blog/sdxl-09-sta...
✩ TRY SDXL 0.9 for FREE Here: www.futurepedia.io/tool/clipdrop
✩ Dream Studio: beta.dreamstudio.ai/generate
✩ Midjourney: www.midjourney.com/app/
► MattVidPro Discord: / discord
► Follow Me on Twitter: / mattvidpro
-------------------------------------------------
▼ Extra Links of Interest:
✩ AI LINKS MASTER LIST: www.futurepedia.io/
✩ General AI Playlist: • General MattVidPro AI ...
✩ AI I use to edit videos: www.descript.com/?lmref=nA4fDg
✩ Second Channel: / @matt_pie
-------------------------------------------------
Thanks for watching Matt Video Productions! I make all sorts of videos here on CZcams! Technology, Tutorials, and Reviews! Enjoy Your stay here, and subscribe!
All Suggestions, Thoughts And Comments Are Greatly Appreciated… Because I Actually Read Them.
-------------------------------------------------
► Business Contact: MattVidProSecond@gmail.com - Věda a technologie
An open source, trainable AI I can run on my own system is the holy grail for me.
YES!
Same, This kills PaytoWinJourney
Stable Diffusion
i have rather old system and stable diffusion runs fantastic for me, sure its not as fast as MJ or Collab stuff but plenty for me. depending on your prompt skills and the model you use i dont see any advantage using MidJourney...
Not only that, but the amount of customisation. I can get a picture exactly like I pictured in my head.
Timestamps courtesy of Deciphr AI 👨💻
0:00:39 - Stability AI's SDXL 0.9 as a serious competitor of Midjourney
0:01:28 - SDXL’s features and real-world applications
0:02:23 - Comparison of SDXL 0.9 and Midjourney through image examples
0:07:17 - Comparison using ClipDrop
0:09:03 - Comparison with different prompts
0:12:21 - Comparison with a creative prompt
0:13:47 - Comparison with a character prompt
0:16:26 - System requirements and availability of SDXL 0.9
it isn't free
These AI tools are getting so crazy, that if you don't use them to your own advantage you might lose your job. To be fair it's good for content creators (especially if used with Famester, which is great for increasing presence on social media). Create content, make it go popular straight away, I like it 😍😁
Haha does that really work?
fyi guys, it's a bot account from Famester running around youtube doing stealth promotions.
12:12 If you look closely at the reflection in the eye on the right, the model decided to place the character in a cave. Truly amazing attention to detail.
The ridiculous censorship on MJ, along with the monthly cost, led me to finally learn Stable Diffusion and I'm so glad I did. I've learned so much about how text to image works, how to craft prompts to match up with models,etc.
Unless this has returned to 1.5 levels of data, its still pretty censored.
what kind of censorship?
@@koffing2073 He's probably trying to create child porn or pornographic image or bloody images
@@koffing2073 You cant make 'violent' images, nothing remotely sexual and a lot of words are banned. This makes it difficult for fantasy artists
@@AIGuy420 no violence makes it useless for video-games, thankfully there is free alternative because there is lots of AI hentai now
You can actually use negative prompts with MidJourney, you just type "--no " at the end of your prompt.
*/imagine blue bear --no brown*
Brain fart. You’re totally correct!
TBH those don't do much. Not even close to the control you can achieve using negative prompts on Stable Difussion.
The --no often radically changes the detail of the image. Maybe I am special, but I avoid that like a blue haired "queer".
--no parameters in midjourney is not that reliable.
@@ellenripley4837 Tell me about it! 😅
Midjourney isn't a raw model, it's a whole system, for example it could edit you inputs to produce what it thinks is "better" outputs and you wouldn't know it, it also has certain settings that you can't change that makes it more consistent but more inherently limited, it could even be picking and choosing which model to use to produce the most compatible results, it could even be using 3d overlay! stable diffusion is a raw model on the other hand that can be used to make other open source systems, that's why the specific stable diffusion models just the ones that are actually being used, currently are specialized models that can surpass midjourney in many cases and it is widely used.
Let's hope. I can't afford midjourney
I tried it, it's really impressive
bro francis I know u can afford $10 a month 😭
@@svpermari0 have you got any idea how many $10 subscription I already have? Lol
@@limon2796 not with all the other $10 subs I already have 😆
@@svpermari0 Yeah, because everyone lives in a first world country where $30 a month is pocket change.
I feel like midjourney 5.1 and 5.2 are still way easier to get a wide variety of excellent images, but for getting to a specific image you have in mind, between various models and extensions, SD already takes the cake. MJ is more fun casually or if you have a vague idea you need a starting point, SD is better for drilling down on a concept you want but don't have the photo editing chops to execute.
Very great point! This new model will close the gap by an incredible amount
@@MattVidPro I agree, seems like it has much better aesthetic understanding instead of being so literal with what you ask of it! Also very glad that they've stated it will run on 8GB of VRAM locally, when I had initially checked out SDXL it seemed like it would need a super expensive gaming PC to even generate images, instead of something accessible to anyone who has built one in the past few years.
I agree. That's one of the reasons why I said in my own comment that when I compare my pros and cons for each, SD wins easily. Personally I've always found MJ overrated, as while the results are important, how you get those results is also important and for me, that's where MJ loses big time.
i kinda disagree, midjourney is wayy better at handling specific prompts more than sd does, you just have to know the right artists mix which will get you the styles you want, which is why sd has to many gaddamn models..because it sucks at getting coherent images nd mixing artists
@@afrosymphony8207 By just using prompts yes. But SD has things like ControlNet that allows you to have specific and coherent poses, you have a lot more control over your image. As an artist that wants to have a specific image that is a godsend. I slowly moved to SD because of that. Most of the problems with it just revolves around the complexity. With Midjourney you can just easily prompt good looking images while on SD there's so much more learning curve and work.
This is huge because now even novices can produce high quality SD images. Most people who try out web-based SD apps give up very quickly because the image quality is really bad compared with the images shared by expert users. Now anyone can produce high quality images with a simple prompt!
I'm glad you finally came to your senses👏👏👏👍👍👍
Looks like a great option compared to the old standard models for new users but I think I'll be sticking with my current setup and 1.5-based models for now. I can already get photorealism with my models and extensions and I have models that can produce images that feel like they were actually taken by a human whereas this model can produce photorealism but it tends towards looking like studio photography with lots of photoshop and compositing. It looks real but also often very contrived which isn't always a bad thing but I tend to prefer a more candid look. I can't deny the quality achieved by Midjourney but I can actually get what I ask for with my current models and with a similar level of quality some of the time vs Midjourney which tends to decide what it wants to give you with little regard for what you're asking for in terms of stylistic direction.
The only thing my current workflow lacks is consistency. 1 in 10 or 20 images will be beautiful and then the others will be puddles of writhing flesh and limbs longing for the sweet release of death so maybe models training on SDXL can improve in that regard. I wasn't surprised by SD's idea of a 35 year old woman, if you ask it for anyone over 30, expect to get an elderly person and you get someone that looks 18-20 if you ask for younger but some of the models improve on that.
Lol it’s so true. Do we have any answer as to why the age ranges are so skewed? In advertising we typically want that “generic 35yo” demographic bc that appeals to most consumers. Unfortunately if you specify age in these AI generators everyone looks elderly 😂
Really looking forward to this release, thanks for the reminder. I may be one of the exceptions to the rule, and it's all subjective, but I've never rated MJ as highly as many others do. Sure you can get great images from it but you can get them from SD too. I don't care if MJ is tecnically better, the pros and cons for each don't make MJ worth it for me over SD, and that's before SDXL lands.
Each to their own though.
It's all about censorship or no censorship. I'd rather less quality with no censorship than amazing quality with full censorship
I'm always interested to see what hive moderation says. On a photographic style I generated it reported 99% AI generated, but not as generated by SD. Instead it came back as 98% likely to be midjourney, which I think gives an indication that SDXL is indeed in MJ territory. When hive update their models I imagine they might then be able to discriminate, but XL does look good and excited for 1.0 and general availability.
nah since loras introduction SD come ahead of MJ, easier to change model/lora for specific use, with often better results
And now it's even better
Stable Diffusion + "mods" has been blowing Midjourney out of the water for a at least a few months now
Still, you have to admit midjourney has some level of fidelity that is hard to match with any form of current modified SD. Imagine what this new model will do!!!
not is hasnt though lol, Midjourney is still king
nope - still no. There is a long way to go with SD. The only chance is to train more and more models. SO far like 99% of a models are same anime waifu or NSTW models of waifu + some realistic ones based on stock photos. Still Midjourney shine in other areas
@@MattVidPro Oh absolutely. What I'm excited about is the derivatives that will come out of the massive SD community. If SD 1.5 which is garbage on its own with mods can come pretty close to MJ, imagine what an actually good base model can do for us!
agreed, people actually using all the models on a daily basis can confirm the suite of tools and models available from SD and the community rival what you can do on midjourney. and has for a while. MidJourney is great for a casual user wanting a pretty image though.
I tested this with my standard prompt test set using the browser interface. The quality was good as advertised, but occasionally the AI failed to understand altogether what I was asking it to do, even in cases where its competitors succeeded well. The human hand may still have six fingers. Photographic images use disturbingly often a large camera aperture.
This video is the little push that you needed to reach the 200 k, congratulations in advance ✌️
Edit: here's my honest opinion about this open source image generator.
I think there is still a huge bias involved in the comparison tbh, midjourney looks a lot, and I mean A LOT better still tbh
Yes, the clickbait BS title is definitely going to help.
title is pretty accurate, was not expecting that, good show!
I actually like the SDXL lemon better: it's actually the shape of a lemon. The MidJourney one doesn't even look like a lemon: it looks more like a stumpy yellow hotdog.
I was about to say the same thing, some people complain about the lemon generated by SD for not having five fingers, but is supposed to be a cartoon character and is not even a human. I mean, Simpsons characters have four fingers and no one complains about that.
These stable diffusion images have some great texturing. Every image had good looking materials
Excellent content kind sir. Gladly subbed and looking forward to more content
It's a serious contender it has some great features built in like background removal and I'm getting closer to what I want quicker
This is actually fantastic. I only tried midjourney a few times and for some reason it couldn't do my hyper realistic photo (for a novel cover) but this sdxx did it in the first try. WHOA>
Open Source Devs are modern Heroes.
I cannot wait for this. SD has always been my go to for most AI stuff but this model is really good.
I was just thinking of updating my image software. What wonderful timing!
I like the UI buttons of stability and the extra tools ie uprez etc...and just bought a subscription for Pro for work. But I have to I've been getting better images with Midjourney ( also subscribed ) overall with less oddness on second regens. The resolution of Stability though is better in some instances and I like that it's just a site and not discord, very fast with the tools. I can see Stability progressing fast and catching up quick to Midjourney.
I feel like the MidJourney devs knew this kinda tech wouldn't take long to make its way to home use and actually be comparably good. It's why they charged the 36 dollars while they could.
I think many of these companies that are pushing A.I. online are really surprised at how quickly open source A.I. is developing.
I mean, we are going from quite weak results early this year to delivering this kind of results in just a matter of months.
We are also seeing the same with chatbots, the leaps in quality and performance is even bigger there and I do feel like the days are numbered for these online models, especially if they are behind a paywall.
On that note, what's really needed with these open source models is a clean package that is easy to install and use, that looks the part and has better supports on none Nvidia gpu's, and even cpu's as a fallback option, after all, ease of use and a clean interface goes a long way in selling a product, and that is where I feel is the major weakness of these open source models that needs to be resolved if they really want to take on these online models, otherwise, most will just take the easy option, even if they have to pay.
Thank you for sharing about it. Waiting for it to be released…
Love your Channel Mental Outlaw!!! It's been great and you have been digging with very good resources. Thanks a bunch.
Wrong channel bud 😆
A very good hardware, software and open source analysis.
Unfortunately I can’t say the same for the artwork comparison. And it doesn’t just come down personal preference.
Based on the examples shown in this video, Midjourney is still notably better at subject /background composition, including focal point and control of eye movement around the canvas. It has superior sophistication of asymmetrical balance, better proportions, perspective, light and shadow, colour, textures and of course detail. Perhaps the biggest difference is the ability to distinguish physical property behaviour such as how hair flows and fabrics drape. The shirt on the women in grey is exhibit A. The Stable illustration was a brutal attempt.
Midjourney is still weak on hands. SDXL may be better in that regard but I didn’t see enough examples to make that determination.
There are at least 5 major things you can do to vastly improve the output and get exactly what you want while in midjourney what you saw here is what you will get.
@@markemad1986Which things do you mean specifically?
@@julianvandieken control net, adjusting settings, using a different model (or creating your own), using a Lora (or creating your own), using reference images, using a better prompt, editing image parts (with ai), and mixing models and or loras.
@@markemad1986 - That's true and the crux of the race - Midjourney doesn't do true image-to-image functionality. I suspect Midjourney will incorporate image-to-image editing before Stable Diffusion catches up in composition intelligence and image quality, but I don't know that because I have no idea how far along either one is in their development. The current releases are just a clue.
My doubts are due to my understanding that SD and DALL-E have a much bigger development challenge to complete - to write the higher level of sophistication into their AI. As compared to a well funded MJ who hired great talent and focused on nothing but the AI first, and now just has to adapt their sophisticated algorithm from a text-to-image generator to a picture-to-picture editor. That's a considerably less complex task.
I'm guessing MJ will soon be deploying a nice new UI with image-to-image capability and likely win the race... but I'm also thinking that won't matter for very long. In the long term the Open Source apps will match or exceed MJ, and, at the very least, drive down MJ pricing to be in line with SD and DALL-E.
Personally I'm pulling for SD. I like orgs that can't be bought out. :)
@@yo-Rowe honestly all my favorite ai images are from stable diffusion. MJ does have a certain feel that I don't like, where stable diffusion can do almost anything and unless it looks like a model I already know images from stable diffusion can be as unique as desired.
Interesting, can't wait until a few months after release when all the Loras and Checkpoint models get updated with this.
I think it'll take some time for it to catch up to the offerings for the current models, especially given that it's likely no good at making naked people like all of the models since 2.0 so that turns away a large part of the market but it'll be interesting to see how it shakes out.
Congratulations on 200k Matt :)
Super! Very nice! I am looking forward to it...Open Source rules!!
After watching your video yesterday, I decided to try it out and I have to say, I'm hooked. I like it so much that I paid for the pro plan...thanks for this
Really helpful video, thanks Matt!
About a tricky functionality of SD: I just don’t want to deal with it! This tool still looks awkward for me, although it has its own interface, in contrast to the stupid text "control" over MJ.
As for MJ, I would be satisfied with such an image control function when you set a prompt for a selected fragment and ask the neural network to correct a specific element, its shape, shade, lighting, etc. And yes, I need PSD format with layers!
I'm relatively new to this, like less than four months. I never tried Midjourney, but most of the people I came across in the BlueWillow community may use that AI as their favorite, but they actively try every AI that they could use. Many of the users are coming from third world countries, me included. Part of the fun is make something amazing with the tools you have. Many AI bots are thriving in Discord, lol, probably there is a niche on the market for everyone.
Wow, the rate of advancement is really amazing!
I mean some of the community trained stable diffusion models and negative textual inversion prompts already allow for stunning images with coherent hands and honestly sometimes completely indifferentiable output. Since you can't train textual inversions on Midjourney, I think a fairer comparison would be Midjourney vs fully modded stable diffusion rather than out of the box stable diffusion.
The way you explain it is so exciting
so.... things like control net won't work on SDXL out of the box, right? Seems it has to catch up to a looooot of features that make SD1.5 so awesome to use right now
This is extremely promising. I hope this will also run as awesome as SD does on my M1 Max.
Thank you for talking about open source with this passion. I am so happy that I can participate in this AI revolution without ever needing to touch any closed-source software other than the f-ing nvidia drivers on Linux
Why not making your own Nvidia driver? 😉
@@SENTRY456123 people who are immensely smarter than me have tried and failed
This is definitely better than some other alternatives. I keep trying to create a realistic image in Mid-Journey of a person wearing a white t-shirt, but no matter what, it always puts a collared, button up short on the person. This one actually worked and put a t-shirt on the person, and made a very realistic person as well. I did noticed it still has trouble with hands, where Mid-Journey has definitely improved in that area.
To get a man in a T-shirt, you can add couple of negative parameters (--no shirt, --no buttons); or even better: You can add a link to file at the beginning of the prompt, where a man in a T-shirt is depicted (or upload your own file and use the link to it). MJ will pick up this image and change your character's clothes.
@@o.k.2968 I am going to try that, thanks!
@o.k.2968 the --no works, but any negative prompt completely changes the results and almost makes it look like an image created with an older version (even though it is set to 5.2)
I consider both essential. They have different feature sets that compliment each other very well. Mj has the prompt generator and a new blend feature, SD can evolve reference images. MJ is king when it comes to fantasy style art, subject placement, perspective, balance, etc. I like to do stuff that looks authentically hand painted, and that's where.mj falls behind. SDXL 1.0 in dreamstudio rules when it comes to that and that's what i like to do. But i can generate amazing images in mj and then evolve them toward that authentic hand painted look in SDLX.
Perfect! Will only get better
I was a big fan of MJ since the beginning. In the past I would see and try Stable Diffusion and would get really bad results. It turns out the original SD models are actually not that good, or may be they are just too broad and basic. After I discovered custom models and loras, all of that changed. SD with custom models, loras, controlnet and other extras is just better in every way. It gives you extreme control over everything you create. Also the upscaling and resolution of generated images is way way better. MJ still have very limited resolution. Something else with MJ is that it is very much focused on close up portraits - it uses blurred backgrounds, shallow focus of small area (the face or part of it) to imitate quality. It does well with lighting too. But when we talk about details, MJ is just still very much struggling. Try getting an animal in forest with flowers, mushrooms and grass for instance. You will always get perfect animal and everything else will be just smudges and deformities or just super blurred background. This is problem when upscaling because the details are just not there. What about inpainting and outpainting? MJ is very much super late with these tools. They released new version with zoom out feature that is basically useless, nobody asked for it and is good only for you to play for fun for and hour or two. The most asked thing by the MJ users is the resolution, option for real upscale and inpainting. To this day I can glimpse an image and in 2 seconds I already can tell if it came from MJ. SD on other hand have so much models and styles it can do virtually anything, and new models are released every day.
The reason so many people stick with MJ in my opinion is that it is just easier to use. But that is what makes it so limited. Yes, launching SD involves a lot of steps, but it is totally worth it. I use it on a cloud GPU for cents per hour and can generate images in 10 seconds. I can generate 8 images simultaneously. Everything's working super fast. The user interface is a little intimidating for some people but in reality it is very easy and useful. I have 300GB custom models right now and I can run a single prompt through all of my models and get comparison of the results and pick the one I like most.
I have around 300-400gb in sd models that i store on hf and locally. Honestly, the only bad thing about sd right now is the hard installation and troubleshooting for people who just got into ai image generation. Yesterday, i had an error while using sd and it turns out my pytorch version was too new.
thank you for a clear and engaging introduction, good visuals (videos, images) in conjunction personal presentation, clear and coherent voice over, organized structure of information, easy for the audience to understand, Concluding remarks summarizing key points - youthful exuberance - engaging audience. SUBBED
Very nice comparison. The AI image gen are very good and still an early stage. I will support financially or coding open source projects over property ones.
Loved your video! You might find Stylar AI interesting for logo and interior design. It's still in development but worth a look.
He's competing with Midjourney now, and he's free ❤️🎉
That's greate!!!! Can we also input 2 images to combine them?
Thanks for your content. Can you please help me to find the right prompt and ai to use to create an accurate scuba diver. I tried mj lexica leonardo.... Not successful
Very cool comparison.
SDXL is nice. But imagine the custom models based on SDXL... Stable Diffusion will murder the competition.
Can this be used on an iPad or MacBook Pro? Great video thank you 🙏🏻 💕
Thank you for the video. I think the platforms' target audience should be touched upon as well. MJ's is not the same as SD's. Those differences are a very important part of why these platforms perform how they do, what they allow, how much control the synthographer has, ease of use, the learning curve, the pricing, etc.
Good video, but I doubt either of them is going to RIP. They'll finesse the USPs and strengths they have over the others. MJ's going to have to keep a keen eye out though, that's for sure.
Well said.
Could you please elaborate on the target audiences for these?
Ok...U Now have my attention. I just Subscribed to U. This looks quite interesting so I think I will give it a try. Thanks 4 sharing buddy. Cheers!! 😎
I guess it really depends on what you're looking for. When I use an AI generative art program, I don't WANT a hyper-realistic, photo like result. I WANT the more art focused result. To say that one is better because it give a hyper-realistic result instead of a more art-like result is ridiculous.
Cool video. You sound a LOT like Carl Sagan!! You look like him too!! 💖
What i am missing in MJ is real capabilities to create replica of portrait (with training) and adapt to prompt as i have seen some demos as controlnet and dreambooth but better as MJ should be able to generate with minimum effort. Their upload image and blend doesn't work so well. Would pay for it
I can't wait for the full release
Same!
All I want for Christmas is a locally run AI text to image generator that is either free or a one time payment with absolutely no censorship
8:00 btw, the resolution of SDXL is not 1024x1024 but 2048x2048
Yes, I have tried it in Clip Drop at length, and it is a major improvement over the previous beta SDXL which was used, but still no AR or img to img.
But why OH why more freaking aliens! Aren't there any good looking humans left?
What about textures? Can sdxl create a texture for game asset or for use in 3d modeling?
A better prompt for SDXL for the glasses would probably be: "wearing augmented reality glasses" or something. Apple vision pro is too specific, and dependent on what text prompts are recognized
.
The timing of this is so good
Asking for Apple glasses is a bit hard as here probably isn't many images of them to reference to
SDXL is 1024 native :)
Didnt understand where and how i can download it to run on my own pc because of lack of understanding english. what did i miss? is there an manual or how to?
Dope Content Matt🤘🏼😎💯💧
The real problem I find with Midjourney, it produces good quality images, but it seems to have a mind of it's own in the images it produces, in a sense, you have some control over the image you want but I feel Midjourney overrules a lot of what you are asking of it, with the aim of producing a pleasing image, and that's fine if you are after a random like image to the given prompt, but it's not giving you much control whereas Stable Diffusion does.
If this new open source one delivers, and you have all the benefits that Stable Diffusion offers, whiles also being able to run it on your own PC, no restrictions and no cost, that would be a far better option then what Midjourney is offering for most of us, and I do feel that Midjourney monthly subscription is going to be hard to stomach for a lot of us when there are alternatives that are free, but if I was an artist, it's the control that would grab me, something the open source ones give whiles Midjourney doesn't, after all, Midjourney is good for creating random like images to the given prompt but it seems quite weak on delivering what you actually want, whiles also taking a lot of liberties on the prompt you give it, all in the aim of creating a pleasing image, but I suspect, more direct control to get the image we have in our minds to the screen is what we really want.
Anyway, looking at the images shown in the video, both look impression and close enough to not matter, especially with a few slight alterations to the prompt, you can get closer to the result you want with either of them, that does offer a big advantage to this open source one over Midjourney, and once you throw in the kind of control that Stable Diffusion offers, I really have to wonder why anyone serious about creating good images, would use Midjourney when there is this alternative that offers you far more control and is free.
about time, we need to democratise free AI MOREEEE
I am curious how it will stand next to Midjourney V6 that it should be out next month too
:3 The new text-to-image does better prompts, does hands good, and is open-source!
Stable Diffusion and other open sourced solutions will still have their place because they offer customization for those that need it. For those that don't want to mess with "all that", there is midjourney.
Can you do a deepfloyd vs SDXL comparison video?
What I want more than anything is a text-to-image generator that can use plain English instead of unintuitive prompts.
This was a great piece, thanks! I will say, as long as midjourney continues to block, and censor the images designers want to create, I have no intention of EVER using it. does this version SDXL .9, or will the final, mid July version allow you do create images that Midjourney considers NSFW?
I agree, I stopped using MJ right away when it kept flagging my images, although I wasn't trying to make anything even close to NSFW. I'm interested to know for sure, but I expect SDXL will be "family friendly" just like SD v2.
Designer?🤣🤣
@@miss_hanne why do you ask? Not seeing your point here.
Can you use the images from stable commercially? Or are they just for personal use? Ty
Stable diffusion is open source so you can use images created if u run the software yourself, but if you use an app, refer to the app’s terms of service. However, technically, the US copyright office has said that the user of AI-image-gen software is not the “author” for copyright purposes. Stability AI is not trying to claim copyright so they’re not going to sue you, but if you wanted to register your work for copyright, you’d need to change it enough that it qualifies as a! “Original work of authorship”
Testing for Clipdrop is limited to 400 images a day, or ~100 prompts. The price however is very reasonable. I subscribed for Relight alone.
I'm actually blown away by how impressive this is. It's as good as MJ, maybe even better.
Matt, you're always better than Santa in person because only you know how to make me really happy. Thanks, Matt. Your videos are real gifts for me.
Do you want some cookies and milk, maybe?...
💀☠💀☠💀
Over 3k views in 1hr...
This is love.
You can dream, but midjourney has no competition
but when i loaded sdxl 0.9 into my stable diffusion it says it cant be used for commercial use. thats not really free
At this rate how much do you think, or how upgrades later, do you suppose SD will leave mj behind?
Less than a year... SD has endless manpower and imagination working on the most amazing things. Endless models and solutions.
And about time for that.
Wow........ this is big!
Thanks a lot. When is Mac users taken into account ? :)
It cannot be installed on a Mac right? I tried to install the libraries but one of them was only for Linux...
Hola! Can this run on a Mac? Or do I need to up grade to a PC??
Great video
btw are there any news of DeepFloyd? I heard it's available for local use for a while now, but noone talks about it
always add this to your prompt in SDXL: no distortion
i just made the midjourney one of the wolf, its perfect, no issues with it