SDXL 1.0 in A1111 - Everything you NEED to know + Common Errors!
Рет қаралды 156,208
Күн бұрынSDXL 1.0 is out. Here is everything you need to know. How to use it in A1111 today. In this video I show you everything you need to know. Everything that is new in SDXL 1.0. How to download SDXL 1.0. How to use SDXL in A1111. What is the SDXL Offset Lora used for. SDXL Refiner Settings in A1111. Using a Trick in A1111 to use only the Refiner Model for image Render.
#### Links from the Video ####
SDXL 1.0 Announcement: stability.ai/blog/stable-diff...
SDXL 1.0 Base and Lora: huggingface.co/stabilityai/st...
SDXL 1.0 Refiner: huggingface.co/stabilityai/st...
Stability Image: / 1684254689250902025
Nerdy Rodert Image: / 1684506233334538246
OrctonAI Images: / 1684344552654610434
00:00 Intro
00:25 What is new in SDXL 1.0
02:40 SDXL Image Samples
04:35 Prompts and Loras
06:01 Ways to use SDXL 1.0
06:43 SDXL Render Samples
08:44 SDXL 1.0 Model + Lora Download
09:41 SDXL 1.0 use in A1111
12:09 SDXL 1.0 Refiner in A1111
13:07 SDXL Prompt and Settings Guide for A1111
15:54 SDXL Refiner ONLY Render TRICK!!!!!
17:08 Thank you for Watching!
@eded4104 11 ай бұрын
Thank you for being one OF THE FEW that don't sensationalize your video to get views,. Just honest straight forward. Don't change....you will prevail much farther than all the others :)
@OlivioSarikas 11 ай бұрын
thank you :)
@geterpriffin 11 ай бұрын
Yes, thank you for not adding 'earn $5,000 weekly' in your video thumbnail and title
@AndyHTu 11 ай бұрын
@@OlivioSarikas But i wanted you to click bait me with uncensored stuff and telling me its better than anything you've ever seen. ;)
@sukhpreetlotey6304 11 ай бұрын
Totally agree...really starting to cringe over those videos
@tlilmiztli 10 ай бұрын
Ironic. This used to be Affinity Photo channel but when AI showed up, almost over night he saw where views are. So... "dont change AGAIN" maybe :D
@HikingWithCooper 11 ай бұрын
Thank you for always making this easy for those of us who are not programmers. I breathed a sigh of relief when I found this video amongst the lesser install vids where they always assume everybody has a professional-level knowledge of doing pulls and tweaking Python settings. So thank you!
@courtneyb6154 11 ай бұрын
Always love your videos. Easy to follow and I like how you explain what you are doing while you're doing it....makes things much more understandable. Thanks for all your hard work!!! Love your accent too! Haha!
@OlivioSarikas 11 ай бұрын
Thank you, my friend
@None_ya_B 11 ай бұрын
Thanks! I was looking for someone who is actually talking about it and not just trying to hype it up.
@MrGrantGregory 11 ай бұрын
Thanks man been waiting to get into A1111 for a while this got me there
@unclehoxAi 11 ай бұрын
that refiner trick is awesome. Very cool discovery. Always appreciate you Olivio
@OlivioSarikas 11 ай бұрын
My pleasure!
@3oxisprimus848 11 ай бұрын
Olivio, I love your energy
@OlivioSarikas 11 ай бұрын
thank you :)
@jibcot8541 11 ай бұрын
I loved the Hacker Olivio, lol , doing great work as usual.
@OlivioSarikas 11 ай бұрын
Thank you. Hacker BOI might come around more often :)
@CHAZZdarby. 10 ай бұрын
First videos of yours I've seen. Instant sub and like. GREAT WORK!
@ArnoSelhorst 11 ай бұрын
Great seeing you improve as you create each episode. Following you for quite some time now and it's obvious you really put a lot of effort in your moderation skills. This said, this episode was one of the most entertaining ones I ever saw on your channel. Keep it up! You rock! 👍🏻🚀
@intangur 11 ай бұрын
Looks interesting so far. Will be interesting to see how it will eventually work out with deforum and similar extensions once they start to get updated.
@AaronALAI 11 ай бұрын
Been waiting for this video, thank you!
@OlivioSarikas 11 ай бұрын
Thank you. Sorry was busy today with another project
@OlivioSarikas 11 ай бұрын
#### Links from the Video #### SDXL 1.0 Announcement: stability.ai/blog/stable-diffusion-sdxl-1-announcement SDXL 1.0 Base and Lora: huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/tree/main SDXL 1.0 Refiner: huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/tree/main Stability Image: twitter.com/StableDiffusion/status/1684254689250902025 Nerdy Rodert Image: twitter.com/NerdyRodent/status/1684506233334538246 OrctonAI Images: twitter.com/OrctonAI/status/1684344552654610434
@sprinteroptions9490 11 ай бұрын
On a lark I tried the Comfy UI install and I'm very glad i did. Beautiful.
@justinwhite2725 11 ай бұрын
I installed Comfy two days ago and I'm pretty addicted with some of the custom stuff I'm doing. It's great. SDXL doesn't have controlnet yet.
@OrctonAI 11 ай бұрын
Thanks for the mention , always great informative videos 🙏
@spinouze5858 11 ай бұрын
Ngl the end was amazing
@ronskiuk 11 ай бұрын
Great tip for that 1111 update in the .bat file, it wasn't working for me with loads of errors but does now! Thanks!
@akhilwarrior 9 ай бұрын
I'm absolutely loving it!
@JohnSmith-vk4vq 5 ай бұрын
Your advice has been very tasty 😊, Thanks!
@sownheard 11 ай бұрын
Yeah 🎉 official release 🙌
@openroomxyz 11 ай бұрын
Was a joy to watch and very informative and clear, well done video, create something cool
@pavel_mora 3 ай бұрын
I was getting really poor results, and I had a tough time trying to find out why. Thanks to you, I realized I was generating images in 512x512, as I did on SD1.5. I appreciate it! 🙌
@boloblack 10 ай бұрын
Thank you! Needed some easy to understand update info for Automatic1111
@RoyD2 6 ай бұрын
great video. Explaining it very well.
@CheapBunny 9 ай бұрын
Pro Tip: Use Happy Diffusion if you don't have a powerful GPU.
@jsk333 10 ай бұрын
Thank you for your consistently informative videos, so easy to understand and full of great stuff!
@OlivioSarikas 10 ай бұрын
My pleasure!
@Xinkgs 9 ай бұрын
Fantastic enjoyable content. Had to subscribe ❤ Keep em coming. 👍
@gingercholo 11 ай бұрын
8 minutes in and you finally get to what I came here for. I can look at websites on my own 😂
@autonomousreviews2521 11 ай бұрын
Nicely done as always!
@OlivioSarikas 11 ай бұрын
Thank you :)
@coloryvr 11 ай бұрын
WOW! Very cool! BIG FANX & Colored Greetinx!
@OlivioSarikas 11 ай бұрын
Thank you :)
@chrisrobinson7728 11 ай бұрын
Thank you so much for mentioning that the A1111 needed updating to work with the new SDXL, that fixed my problem with it not working. Nerdy Rodent, did a great video, but made no mention of this!
@OlivioSarikas 11 ай бұрын
you are welcome :)
@ManuelJimenez1 11 ай бұрын
Amazing! Thanks you Olivio
@user-xn9yu4tr6j 11 ай бұрын
you are an absolute legend
@RollieHudson1 10 ай бұрын
Love the sunglasses for ‘hacker mode.’ 😂
@mattfx 11 ай бұрын
Great video and amazing look with glass !! 😆
@OlivioSarikas 11 ай бұрын
Thank you!! 😁
@TeeEss 10 ай бұрын
As always I am amazed at your content and explanations - when do you ever sleep?
@danielfaraday8197 11 ай бұрын
I'm lucky this year. Another superb discovery of a channel 🙂 Olivio, I have one question - can I use my own image source to generate a graphic where Im situated on a different planet and drinking some fine gin? 😅
@scottgust9709 11 ай бұрын
Great vid BTW,subbed :)
@kenpa0048 11 ай бұрын
A great video as always, with the plus of hacker Olivio 😂
@felipenl6753 10 ай бұрын
Thank you Olivio for your great support and detailed explanation. One question, when trying to download the SDXL base model and the SDXL Refiner, I can see that today exists now the versions including VAE for both models. Is there any suggestion from your side to select the VAE or not VAE version to download and use?. Thank you.
@rolarocka 10 ай бұрын
SDXL is indeed amazing 🎉❤
@JohnMcG 11 ай бұрын
Very informative video, thanks. Unfortunatley as a linux user I have tested this on 2 seperate machines on automatic1111 and had consistant errors with loading the refiner model. Hope that it gets sorted soon as it looks great :)
@00042 11 ай бұрын
There is nothing unfortunate about being a Linux user ;) Which distro?
@yoad734 11 ай бұрын
Thanks! Awesome video! Can you please release your automatic 1111 layout (e.g extensions, models, favorite settings etc)?
@ArchAi3D 11 ай бұрын
great, like always, thank you
@OlivioSarikas 11 ай бұрын
Thank you
@parsley8188 11 ай бұрын
Awesome!!!
@ForsgardPeter 10 ай бұрын
Thanks for your content. It has been so helpful. I have been a pro photographer for more than 35 years and this AI image creating is one of the most interesting things that has happened during my career. It will one new thing that I will be using in my professional work. I am so happy that I got to see this development in image making. I tested the SDXL 1.0 model and I am having hard time to get a natural looking skin. The images looks nice and in most cases the anatomy is next to perfect, but the skin looks too plastic. I personally like the old fashion natural looking skin. Any ideas?
@OliNorwell 11 ай бұрын
Great video, right now I'm enjoying SDXL a lot and getting some very decent stuff generated. Though things will 'go nuclear' once we have a series of custom models out and ControlNet works with it. My only fear is VRAM. I can't wait to do Dreambooth with this, but I assume that if we're using 1024x1024 as source images then VRAM requirements are going to skyrocket?
@martinperez1683 11 ай бұрын
Tnx for the update, love this channel. Question: I'm at hugging face and i see a file uploaded two days ago, should I install "1.0_0.9vae.safetensors" or "1.0.safetensors"
@Macieks300 11 ай бұрын
Finally! I was waiting for this video. I tried updating A1111 today to v1.5 on my own but it works way slower for me for some reason. Even for normal SD1.5 checkpoints. I was hoping to see you talk about the command line arguments and tips for them but I guess you skipped that part.
@OlivioSarikas 11 ай бұрын
You might try to delete you venv folder and restart A1111. It takes a while to set everything up again. also try to use --xformers in the command args
@Avalon19511 11 ай бұрын
@@OlivioSarikas Same here speed for me is terrible takes between 4 and 5 minutes for one image even with xformers activated
@Steamrick 11 ай бұрын
You're probably running out of memory... it slows way down if the total video memory used is bigger than your GPU's vram. SDXL might *run* on 8GB of VRAM, but it's not happy until you have 16GB, at least right now. I think I've read that comfy UI does better, so you could try that.
@Macieks300 11 ай бұрын
@@Steamrick I have 12GB of vram but I wasn't even talking about SDXL. The regular SD1.5 checkpoints all work 5 times longer after update to A1111v1.5 than what I was using before which is A1111v1.3.
@philm325 11 ай бұрын
@@Macieks300I had this happen before and auto1111 wasn't using the gpu. I had to update the python torch files ro latest version, it was ok after. Search for a tutorial on it.
@pinn 11 ай бұрын
thank you man
@trungkieninh9066 11 ай бұрын
Great video as usual. But does controlnet works with SDXL
@chyldstudios 11 ай бұрын
Your videos rock!
@OlivioSarikas 11 ай бұрын
thank you
@dferr18 11 ай бұрын
Instantly subscribed bro. Your content is definitely for me!
@cowlevelcrypto2346 11 ай бұрын
YAY ! :P
@PatrickBaitman735 10 ай бұрын
Love the Hackerman xdd
@micbab-vg2mu 11 ай бұрын
Olivio, based on your instructions I installed Invoke AI 3.0. Stable Diffusion XL 1.0 works quite well even though my GPU is not great, only 12GB RAM - the image generation is fast. I use Midjourney prompts and in some cases achieve even better results. Thank you for the tips.
@OlivioSarikas 11 ай бұрын
awesome!
@linusgustafsson2629 11 ай бұрын
Noticed my WebUI was just an unpacked zip-file, so I went to start over with cloning down the repo this time to easier keep it updated. Taking a while, but hopefully it will be worth it. The safetensors also take a long time to download so I imagine a lot of people are downloading them to enjoy themselves with AI art.
@Frankenburger 11 ай бұрын
11:15 you don't HAVE to use 1024x1024. In my testing, SDXL can generate images as low as 768x768 without suffering severe quality loss. This is useful for lower VRAM systems, like my 8GB laptop, since it allows you to generate 768x1024 (portrait) or 1024x768 (landscape) images while saving a little bit of vram. I have even done 1280x720 images featuring a kitten wearing knight armor with very little quality loss compared to 1280x1024.
@MyFather95819 11 ай бұрын
How are you doing it? Its apparently not working on my 8gb Rtx 3070, is there any other way to make it work? For me it only works if i write 2 word prompts and just makes awful results
@CoffeeAddictGuy 11 ай бұрын
Is speed of 768x768 image generation the same with sdxl1.0 vs sd1.5 or is it noticeably longer? Will you be able to upscale that 768x768 to 1024x1024 in img2img using the refiner with similar result?
@MrMsschwing 11 ай бұрын
@@MyFather95819write --medvram in start bat file, that worked for me
@Frankenburger 11 ай бұрын
@@CoffeeAddictGuy SDXL in my testing is about 25-30% slower than SD1.5, but it's hard for me to get exact numbers since I have to use --medvram, which does change the performance a bit. Also, yes, you can render 768x768 with the base model and upscale it with the refiner to get better details in img2img. If you go to Civit and search @frankenburger you can find my test images that are a result of this method along with their metadata
@Frankenburger 11 ай бұрын
@@MyFather95819 I'm not sure what you mean by awful results, but I'm not using a1111 any differently with SDXL than I was with SD1.5. Without being able to see your settings, I'd like to suggest going over to Civit and searching @frankenburger. I posted sample images that were rendered at 768x768 using the base model (and then upscaled them using the refiner) and included their metadata for your reference.
@frankhall401 11 ай бұрын
I tried the prompt, "a perfectly normal man looking at his perfectly normal hands"... SDXL produced a handsome man with seven fingers and three thumbs!
@timothymonaghan433 11 ай бұрын
@OlivioSarikas The charts were generated with results from blind image generation. People could vote on thousands of images. The choices were side by side and nobody knew which models were being used to generate the images. This is how those results were generated in the graph.
@OlivioSarikas 11 ай бұрын
I know, but that still doesn't tell us much about how good the really is. Of course it is better than SD 1.5, but we still have to see if the trained models from the community are far better or just a little better. Of course also the improvements will be less big, but more precises over time.
@agatitytube 10 ай бұрын
Thank you, it is great. I saved your video. Is there any video from you about the step-by-step installation of A1111?
@user-vs3qg4zs8s 11 ай бұрын
Thanks for the info Olivio, I am trying to understand if there is a way we can use one of the model to batch process multiple images with the same treatment to get similar results on all the images of the same batch, any guidance would be highly appreciated.
@FishzWorld 11 ай бұрын
Nice
@BlueScorpioZA 11 ай бұрын
For me, the best way of using SDXL so far is to set up a second copy of Auto1111 alongside my normal version - run it clean with no extensions installed, and the --no-half-vae --opt-sdp-attention --medvram command line options. Works like a charm, and it's pretty fast as long as you have the right drivers installed.
@okachobe1 11 ай бұрын
--xformers might help with the speed as well with that setup
@gulfblue 10 ай бұрын
How do you go abouts making a second copy of A1111? Did you just reinstall A1111 in a new directory?
@okachobe1 10 ай бұрын
@@gulfblue zip the original folder and then install the new install
@gulfblue 10 ай бұрын
@@okachobe1 I have no clue what that means... Do you mean zip the current SD folder I have so that it can't be affected, install SD again, and then what? Can I unzip my folder containing my original SD and use one for SDXL and one for the previous?
@tom.shanghai 11 ай бұрын
I've created a simple extension that uses the refiner for the hires fix pass but it requires a minimum of 32gb ram (not vram). But lets hope that we'll get a native way to use the refiner in A1111
@tom.shanghai 11 ай бұрын
@@user-jm4cd5sd1x a1111 need much more ram for sdxl then comfy ui on my system..
@KolTregaskes 11 ай бұрын
You can see why Midjourney want v6 out as it will intrepert text better than v5, which seems to be one of the big features of SDXL. MJ is still generally better even at v5 but SDXL is very very close now.
@erickromano5030 11 ай бұрын
This model checkpoint doesnt load for me, always get back to de last one i have used... you know why? Failed to load checkpoint, restoring previous size mismatch for model.diffusion_model.output_blocks.8.0.skip_connection.bias: copying a param with shape torch.Size([320]) from checkpoint, the shape in current model is torch.Size([640]).
@TomiTom1234 11 ай бұрын
Thank you for the video, you saved me a minute of rendering by using this "HACKER" method. I was struggling for this issue, since I have 8 gb VRAM card, and the rendering takes like 1,5 minute to render on the base model, which led me to use ComfyUI which is much faster and stabler. But it needs some learning to add nods for refiner and Lora etc.. But you saved me man thank you! I am waiting for your videos on how to train our own Loras and models for this specific model, is it the same like before? Is there any change? All this will keep me busy watching all upcoming videos about this new version.
@OlivioSarikas 11 ай бұрын
You are welcome :) It's not supposed to be used that way, but i think the results can be pretty nice too :)
@Bericbone 11 ай бұрын
The refiner model should not be used for img2img. It's made to work with LEFTOVER NOISE from the base model. The refiner does not work very well on Gaussian noise added to a fully completed image. You need to wait for auto1111 to support the refiner model to use the it correctly, or switch to a comfyui workflow that uses it correctly. You can see it working in this video, adding some detail, but it has little understanding of the image so it also morphs the skin texture completely.
@johnnyc.31 11 ай бұрын
I’m not understanding your description of the proper use for the refiner model. I also don’t see what you say it’s doing to skin texture. Honestly both images at 15:02 have a very airbrushed / unrealistic painted style with little to no texture in the skin. Not the most impressive example image.
@digidope 11 ай бұрын
@@johnnyc.31SD next has option for using refiner or not. It's (probably) coming to A1111 soon. img2img is not the way it's meant to be used.
@OlivioSarikas 11 ай бұрын
Yes, but this is the only way to use it in A1111 for now. So it's better than nothing for people who don't want to use a different UI.
@openroomxyz 11 ай бұрын
Yea it does not feel it does much in which UI is it supported to work correctly ?
@Bericbone 11 ай бұрын
@@openroomxyz StableSwarmUI or comfyui
@sazarod 11 ай бұрын
Killer vid! Question: what is that “apply colour correction to img2img” setting you’ve got - is it an extension?
@OlivioSarikas 11 ай бұрын
i used that for a batch render in img2img tutorial to create videos there instead. haven't used it since
@AlexJota11 11 ай бұрын
Hey Olivio, thanks for making the tutorial. How do you get the Clip Skip and the VAE selector up there?
@Elias-nj6gi 11 ай бұрын
Settings -> User Interface -> Quick Settings List Add "CLIP_stop_at_last_layers" and "sd_vae" Apply settings -> restart automatic1111
@johnleighdesigns 10 ай бұрын
Great stuff really helpful - as a photographer and designer getting into AI generation its amazing to get these supporting tutorials - For me my desktop AMD PC with NVIDIA Super 1650 is very slow using Automatic 1111 it takes around 20 minutes to get one image generated and so this is not practical for me so im looking at options of updating spending £300 on new GPU or other alternatives
@Resmarax 10 ай бұрын
That sounds a bit excessive. Was this with SDXL using 1024x1024 resolution?
@johnleighdesigns 10 ай бұрын
@@Resmarax hi yes it was - super slow - its faster to use somehting like clipdrop but its rather restrictive - will see about spending out on a new GPU and read up if my AMD processor has any influence
@jayceetravel7601 11 ай бұрын
I have a RTX 3090 , aside from xformers do you have any other command prompts you recommend I add? Thanks
@juanserranos2006 11 ай бұрын
Excellent tutorial and information @OlivioSarikas but I was wondering, and if is not too much to ask... What is the Automatic 1111 that you are running, because I don't have some of the slide controllers (like the Clip Skip), and option windows (SD VAE), that you showed in this video. Is this part of a default installation of Automatic 1111, or are there extensions that you have to install? One more time thank you for your excellent videos. Take Care.
@user-yj3mf1dk7b 11 ай бұрын
check settings
@DiffusionHub 10 ай бұрын
no extensions, you need to enable them in your settings
@widowmaker7831 10 ай бұрын
The images you are showing I'm wandering if it's just my screen but they appear to have vertical lines on all around the edges of the characters also through the characters. Is this a shortcoming of the AI or perhaps the way its transferred to this media? Also the image at 2:50 an improvement would be for the AI to render in the foot prints from the dog running and jumping in the sand, at the speed it would have to be running there would in a real pic be prints left in sand and also more than likely sand flung out from the dogs back paws. Just some observations.
@drecksyutube 9 ай бұрын
I like the hacker mode^^
@SkizzieSpeedruns 11 ай бұрын
Hello, is it possible to get it running with Vlad automatic? So far I haven't seen any tutorials for it.
@cptgrimm 11 ай бұрын
Please make a video for SDXL 1 within Comfy!!
@swenfoxington9721 11 ай бұрын
Is Controlnet already available for SDXL 1.0 with Automatic 1111? Couldn't find anything on the web so far
@JOnline-im2wz 11 ай бұрын
I was getting poor quality results and errors most of the times. Now I know why. I had my vae set to 84k. Lets try out with new knowledge. Thank you!
@OlivioSarikas 11 ай бұрын
awesome, happy i could help
@CaptainKokomoGaming 11 ай бұрын
How will this one fare with lower end users? 2060 ti super and lower? I have to use --lowvram in the arguments. Will I need xformers etc.?
@Searge-DP 11 ай бұрын
There were discussions about the SDXL 1.0 VAE and how it created some strange artifacts, a lot of people seem to recommend to use the SDXL 0.9 VAE with SDXL 1.0 to avoid those issues. Maybe worth a try to see if you still get those problems with the eyes when not using face restore.
@HaohmaruHL 11 ай бұрын
So far I didn't notice any difference when I use SDXL 1.0 VAE compared to when I use None. I have Restore Faces checked. If I don't then faces suddenly all turn blue and distorted in the last Step using the 1.0 VAE. Gotta try 0.9 VAE then.
@Cutieplus 11 ай бұрын
@@HaohmaruHL Try set --no-half-vae
@HaohmaruHL 11 ай бұрын
@@Cutieplus is it when editing the .bat file with a notepad?
@harnageaa 11 ай бұрын
@@HaohmaruHLi think ye
@marhensa 11 ай бұрын
they reupload the SDXL VAE several hours after they publish original SDXL VAE, i thought it already fixes that strange artifact.
@AndyHTu 11 ай бұрын
You and Sebastian are my favorites. The real AI OG's in the industry. How can I trust you to not be an AI Olivio? Real question. Where do you see what version of SD you're running? I keep trying to update, but it says I'm already up to date, fine, but how my SDXL isn't working. It just load :(
@Steamrick 11 ай бұрын
Amongst other places, it'll spit out the version number in the cmd dialogue right beneath the python version and all of the version numbers are listed at the bottom of the A1111 UI. I really don't see how you could possibly have difficulty finding them?!
@Elwaves2925 11 ай бұрын
I had that problem and the solution I found was to do a fresh install with the latest A1111 webUI. Even if it says you're up to date, you aren't. You'll know for definite as it will tell you it's 1.5.0 or 1.5.1 where Steamrick mentions. You don't need to get Python again but remember to add it's path to the webui-user.bat. @Steamrick The A111 webui doesn't show it's version number for all installs. For older installs, those UI numbers you mention didn't show the UI version, they started with Python. 🙂
@OlivioSarikas 11 ай бұрын
thank you. at the very bottom of the browser page OR at the start in the CMD window when you load
@andrewmccarty 4 күн бұрын
Do I need to install the SDXL base model in order to use SDXL checkpoints from CivitAI?
@ltqeex 10 ай бұрын
Amazing content!! Could you please do a tutorial on StableSwarmUI?
@OlivioSarikas 10 ай бұрын
I will look into it
@user-yj3mf1dk7b 11 ай бұрын
will automatic add correct way to use model + refiner?
@cyberhard 11 ай бұрын
I'll start using SDXL when ControlNet is available for it.
@_l3m35_ 11 ай бұрын
SDXL is huge, heavy and it's already excluding lots of users with low/mid-end machines - the world is big and there are users with all kinds of hardware and internet connections. There are LoRas with almost 1GB being produced. Yeah, "show must go on", but I see developers jumping on XL wagon and quickly dropping SD1.5 with some concern.
@leslieware_photography_imagery 11 ай бұрын
So what is the Resolution of the Renders?
@user-hb6dd9iu9g 10 ай бұрын
I tried to upload sdxl with cagliostro but it didn't work.. does it need some new colab notebook? (my pc is too week for all of these)
@ritpop 11 ай бұрын
the roop works for me (colab)
@cobrac4t34 2 ай бұрын
Updated to A1111 1.8.0, when loading SDXL check point getting error. size mismatch for model.diffusion_model.output_blocks.8.0.skip_connection.bias: copying a param with shape torch.Size([320]) from checkpoint, the shape in current model is torch.Size([640]). I'm assuming something broke related to SDXL in this latest A111 update. Any suggestions ?
@peterhosfield 10 ай бұрын
has there been any new insight into minimum specs for this?
@aero8057 11 ай бұрын
I'm on a RX 6750 xt in linux, the terminal shows me "Killed" when I try to load the sdxl 1.0 base model... with 1.5 works well, any solutions?
@rendez2k 11 ай бұрын
"Well call me Bob and butter me sideways" is the best line in any KZfaq video this century, and this is FACT 😀
@MrHannessie 11 ай бұрын
The first that is not shouting MJ killer, nice! Since it is not, at least not right now.
@victorwijayakusuma 10 ай бұрын
thank you for this video I got error when using SDXL size mismatch for model.diffusion_model.output_blocks.8.0.skip_connection.bias: copying a param with shape torch.Size([320]) from checkpoint, the shape in current model is torch.Size([640]) please help
@coreyhughes1456 11 ай бұрын
I can't bring myself to do extra steps to get worse results than 1.5 at a much slower speed. I'm going to hold off for awhile!
@CMDRRustyDog 11 ай бұрын
Pretty sure also that in the webuser.bat file you need to add the argument " --no-half-vae" for SD-XL 1.0
@bladechild2449 11 ай бұрын
honestly, I've tested some of my prompts from 0.9 on 1.0, and it feels worse? Maybe it's just the RNG effect at play with prompting, but I had a lot more success with 0.9 when it came to making artistic images. 1.0 seems to heavily latch onto a specific part of the prompt and never deviates from anything else you put in. You can put a prompt like "actress sitting by a cafe window by insert artist", and then add something like "bold line art, intricate lines..." etc etc, and the image will look the exact same. except she has a skirt on instead of trousers. It's weird.
Bitesized Genius
Рет қаралды 180 М.
Огород Логинова
Рет қаралды 6 МЛН
Gadget Baby
Рет қаралды 32 МЛН
Огород Логинова
Рет қаралды 6 МЛН