March 2024 - Stable Diffusion with AMD on windows -- use zluda ;)

[@taffyware1059]

Performance better, worse or equal to Linux ROCm?

[@FE-Engineer]

about 20% - 25% worse than ROCm on linux I would say...but has all the normal features of automatic without any ONNX or Olive stuff that were very irritating.

[@taffyware1059]

@@FE-Engineer ​ Ig its better than having to the all the optimization stuff over and over again, also likely a lot less space is consumed compared to duel booting linux

[@FE-Engineer]

Yes. If you hate the idea of dual booting Linux. Or have other reasons why Linux ROCm is not an option. This is a reasonable work around.

[@ml-qq5ek]

​@@FE-EngineerI am only getting 1-2it/s on 6900xt with zluda. What is wrong

[@HamguyBacon]

@@FE-Engineer I used ventoy to run linux and i don't see where people say its easier to install and use, i had a hard time trying to get SD to even run.

[@shefu689]

THANKS A LOT MATE! This is so awesome. I have played with directML and its settings before like hell. My command webui-user.bat argument lines were almost one A4 page. i noticed that you need to restart your PC to get new PATH directions to work on WIN11. Without restart you end up getting "failed to load zluda path automatically" and "use skip-cuda-torch-test" info. Also first install will download cublas64_12 and cusparse64_12 instead of 64_11 without using --use-zluda argument with user.bat.Idk why. My 6750XT results: 1. 1.5 SD models: txt2img 1024x1024: 3.75s/it /average and 1:05min generation time. SDXL models: txt2img 1024x1024: 3.50s/it average and 1:10 minutes. NOTE: without zluda this was impossible task because instant memory error. and SDXL models generated over 2 minutes with 512x512 resolution. 2. Memoryusage is now calibrated. With zluda SD using only 10.2gb/12Gb memory and it will free up memory after generation. 15min 1024x1024 -> 2048 upscaling did not encounter memory error. With directML you cant use more than 1.5x upscale and controlnet. No you dont need a control net with zluda. This is awesome. 3. ControlNet works just fine 4. Ultimate Upscaler works normally 5. Inpaint works normally AMD pro drivers are slight faster than adrealine version. There is sligh 5-15s delay with adrealine when press "generate" and no delay with ProDrivers. IDK what cause this.

[@SanyaWoFloride-k5u]

How it worked for you.. i've got Cannot read C:\Program Files\AMD\ROCm\6.1\bin\/rocblas/library/TensileLibrary.dat: No such file or directory for GPU arch : gfx1031 rx6700xt, with no working workaround on that shlt

[@МишаЛысенко-я3ю]

@@SanyaWoFloride-k5u you need ROCm 5.7.1 and change files in \ROCM\5.7\

[@swietypiotrprzykurwiciel6488]

I just bought a new card and once again I am back to your tutorials. Your videos helped me before, your tutorials are extremely up to date and easy to follow. Thanks man, you're doing a great job here!

[@FE-Engineer]

Whahoo! Glad it worked and went smoothly! :). Thanks for watching!

[@matthew78917]

I “sidegraded” from an RTX 3070 to an RX 6800. Mainly did it because I wanted that extra VRAM and I found a really good deal. Thank you for this tutorial! Very well put together

[@CapaUno1322]

Me too, just found a bargain rx6800, this is my best ever card and apart from the bells and whistles this card punches well above it's weight....

[@jk-ze2bo]

This was a lifesaver! Fiddled 2 days to get Olive ONNX etc working at at least useable level, and after installing zluda using this tutorial (almost) all works out of box without constant tinkering. Inpaint sketch does not work proper (renders whole image instead mask area) but it is prob -directml fork issue

[@FE-Engineer]

Overall if users don’t want to go Linux and for real rocm. And until complete rocm is on windows. I think zluda is an excellent compromise that still provides tons of functionality for folks in windows. Thanks for watching!

[@FormalPluto]

Very nice tutorial. I've moved onto the NVidia side, but your tutorials were extremely helpful with setting up SD with Olive when I was still using my RX 7800XT. Thank you for making it easier for AMD users stuck in windows who are curious about trying SD.

[@FE-Engineer]

Thank you :)

[@f1amezof]

Very nice, because it doesn’t work?

[@FE-Engineer]

This goes back and forth. About a year ago price / performance was on the side of amd mostly but due to continued improvements now nvidia likely has an edge if you can get a good price for like a 3080 or even maybe a 4070 super. With AMD. Yes. Linux will give you better performance 99% of the time because full ROCm.

[@jcdenton23]

OMG! I can't believe this worked! I'm running this on a 7800XT with no issues. One thing to note though, this only worked with Python Version 3.10.6. And also, for anyone not following FE-Engineers file location and structure, you can run CMD from the address of the file explorer window, just navigate there and type in "cmd" in the address bar and command prompt will open at that directory, made things a bit easier for me.

[@Briannoger-j1w]

Thank you so much for this tutorial! Haven't even finished the entire video yet but already started generating, even without replacing the files (which I did anyways, didn't seem to affect speed). Getting around 20-25 it/s which seems great! 7900XTX sure is a beast of a card!

[@FE-Engineer]

Yea they changed some things to make it a lot easier.

[@LeshaKhaletskiy]

You are the only person who have workable SD XL AMD guide , also whole other stuff like torch, torch-cu, tensor work well, and this rare

[@darthilli]

[WinError 126] The specified module could not be found. Error loading "C:\Users\___\ZLUDA\stable-diffusion-webui-directml\venv\lib\site-packages\torch\lib\cublas64_11.dll" or one of its dependencies. please help

[@sujimayne]

Just FYI, you can use a Windows variable %userprofile% to provide an actual full ksth that can be zsed in Windows without exposing your username.

[@silvermoonk9121]

Make sure u copied the 2 files he mentioned and renamed them correctly.

[@darthilli]

@@silvermoonk9121I worked it out, all good 😊

[@bongpng]

same error here, did anyone solve it?

[@3vilful]

newer version of zluda has fewer files or am I missing g something?

[@jokinbv5715]

Thank you so much. 10 images at 1024x1536 (Hires fix from 512x768) 7900XT With previous directml: 16min Now with Zluda: 5min 30s

[@FE-Engineer]

Whoah. That’s way better! Nice!

[@MathieuCruzel]

Thanks a lot for the tutorial. I could not for the life of me get it to work on Fedora and finally this works really well. I moved from a RTX 2060 to anew 7900XT recently and I was getting 1.5x 2x performance on Comfyui but with this I get at last x5 x6 speed when generating with XL Models.

[@CapaUno1322]

Hi there, I'm looking at a rx6800 and so just to ask you're quite satisfied with the performance and capabilities of your 7900XT as opposed to the 2060? I have an rx5700 which I am really happy with though for the AI I need more Vram....

[@MathieuCruzel]

@@CapaUno1322 yes definitively. With the 20G of Vram I can run 7B params local AI in Vram with LM Studio and for ComfyUi it's night and day but moving from a 5700XT to a 6800XT I'm not sure the difference will be as big as the gap between a 2060 and a 7900XT. That's a 2 or 3 generation gap for me.

[@andresalcaino7570]

It work using a rx 7600 xt, thanks for this amazing tutorial, the only one that really worked for me. Like and sub.

[@FE-Engineer]

You are very welcome! Thank you for watching!

[@bernardy91]

Finally, after days of trying, i found your video...really good explanation, and i was finally able to make it run

[@FE-Engineer]

I’m glad it helped! :) thank you for watching!

[@Gawdzend]

I started with one of your other videos, but this one got me officially up and running (on a 6600XT). Much appreciated!

[@FE-Engineer]

Glad it helped and worked without issue (hopefully). :) thank you for watching!

[@White-yz4kw]

What is the generation rate of it/s with zluda? Is the generation faster than with directml? Interested to know before installing, I have a rx6600.

[@Torva01]

​@@White-yz4kwsame doubt

[@ottomanherox]

@@Torva01 sounds like if you've ❌ on HIP SDK it's about 3 times slower than Linux ROCM, atleast according to one test with 6700 XT. Safe to say it'd be memory efficient regardless and I'm tempted to try on 6700 but I've to check if it's useful for something else like DLSS maybe because that speed gain is not worth it alone.

[@ottomanherox]

@@matthewfuller9760 I've tested it. It's about same speed as shark/vulkan but it didn't do much to help VRAM usage. Well, it consumes less than directML but falls apart when you try to upres on sdnext.

[@figure17tsubasayhikaru43]

Hi your video was really helpful some months ago, but it seems that one update changed something and now there are some errors, do you know what causes: "OSError: none is not a local folder and is not a valid model listed on 'huggingface models' if this is a private repository make sure to pass a token having permission to this repo either by logging or by passing 'token=' And Failed to create a model quickly; will retry using slow method. Those are the errors I'm getting, I hope you know how can I solve them 🙏.

[@TPkarov]

For the OSerror, you need to go in requirements.txt and requirements_version, and change diffusers==0.29.2 and transformers==4.30.2, then run again !

[@horrid8024]

OMG! Thank you so much for this one! I tried for so long to get this running... All the text tutorials were just too complicated.

[@FE-Engineer]

You are welcome! I’m glad it helped. Thanks for watching!

[@PSYCHOPATHiO]

Excuse my language... HOLY SHIT, This is good. I gave up on Windows & been on Linux for a while but now after testing ths on Windows... oooh i love u. I can finally utilize my 7900 XT to its potential. Thank you for the easy tutorial

[@FE-Engineer]

I know right? It’s sooooo good! While it isn’t perfect. And I still want full rocm on windows. This is in my opinion a very reasonable not quite full rocm alternative finally!

[@PSYCHOPATHiO]

Having to juggle between windows for gaming and Linux for AI was frustrating, but this just so fast, even more than when I was on Linux. Thanx for the work, as I'm sure I'm saying on behalf of the whole AMD community :)

[@jinxPad]

great stuff! Great tutorial as always, thank you.

[@FE-Engineer]

Thank you so much for watching :)

[@jimmyjupanu]

How to uninstall torch-2.2.0+cu121 and install torch-2.2.0+cu112 , i think that is my problem because when i run sd i run with cpu

[@fmenguy]

Thanks for your tutorials, they are really well explained. For others like me who have an old config: I tried, even though I knew very well that my gpu wasn't on the list. If you get this message: "rocBLAS error: Cannot read C:\Program Files\AMD\ROCm\5.7\bin\/rocblas/library/TensileLibrary.dat: No such file or directory for GPU" it's dead!

[@tolly_HD]

What exactly do you mean with its dead? I also get this error even tho I have an RX 7900 xtx which is most definitely completely supported

[@daveroff4389]

I knew my RX580 wasn't anywhere on the list, but it's 8GB VRAM, so I tried it anyway, and it works! Had to replace those library files (third option), put in a couple of ARGS in user.bat (--use-zluda and --no-half), but that got it working. Only issue is how long the image generation takes, which is like 10-15 minutes. I know it's running on the GPU instead of the CPU, because I can hear the GPU's fans working harder, but is there a good way to speed it up, without breaking it?

[@OfficialGundiminator]

You are the best, sir. I have been struggling with getting my 7900 XTX to work with anything. Only one I got to work with Windows was Amuse, which is very lackluster, and it seems like it's dead at this point, and SD.Next with a workaround, which is not great. With the workaround it lacks the ability to run bigger batches, upscaling, inpainting, the pics look choppy, and a lot more. Not great, tbh. And with Linux, that was just a mess. Most wont open, and the few that works will only work of my cpu. But with your help, I can finally generate pictures with all the features. All hail the king!

[@MortisDG]

I was really getting frustrated with all that shit.. Thank you so much for this video! Finally I can use SD properly again 🙏

[@TrackmaniaKaiser]

Thaaanks a lot for your video! After I spend about 24h bricking everything I finally stumbled across your channel! You helped me get my SD to run so much better than before! I'am looking forwared to your next video with some more SD otpmizations for windows users :) Up to that point? Is there a paypal or something where I can buy you a coffee? You safed me from insanity!

Gracias , hasta ahora encuentro un tutorial funcional, funcionando con una RX6650XT . Saludos en español comprendo el ingles pero no tengo buena dicción. Gracias

[@CapaUno1322]

I just got a bargain rx6800 as I heard that you can do the AI stuff without mortguaging your house to Nvidia, and rx6800 is only 20% slower than an rtx3090 and a new one is half the price of a used 3090 so eh, so here I am trying to get it to work....thanks for your videos....good work! ;D

[@koltendavis969]

Did you get this to work with the latest SD Direct ML? This tutorial as is is too old and I am getting errors.

[@theknightowl2137]

Any ideas how to fix the "Failed to create model quickly; will retry using slow method" ?

[@danielitsfine9818]

Thank you for this. Using onnx and olive was kind of great, getting faster it/s but not being able to use loras and converting models made it not that enjoyable, but it was still good to learn and practice with.

[@koxu857]

can't even imagine how tough was that to work it out. Thanks!

[@Mike-ss1ju]

Thank you so much for this. 7900xtx is finally worth it. I had to disable intigrated graphics in bios to get this to work. Excellent instructional video. This shit is crazy.

[@FE-Engineer]

Ah yes. You could likely set it in windows variables I think it is hip gfx visible devices and then set it to 1 but it works disabling bios as well.

[@auchucknorris]

jsut got stable difusion installed, failed cuda test then you poped up, thanks heaps

[@f1amezof]

RX 7900 XTX I followed step by step, but getting this error: “rocBLAS error: Cannot read C:\Program Files\AMD\ROCm\5.7\bin\/rocblas/library/TensileLibrary.dat: No such file or directory for GPU arch : gfx1036”

[@FE-Engineer]

…its seeing your integrated GPU… Either disable it. Or put in hip visible devices = 1

[@f1amezof]

@@FE-Engineer Hah, I guessed it before seing the actual answer (gfx1036 is not 7000 series), and it works now. But thank you anyway :)

[@nenadm5747]

​@@FE-EngineerWhere to put that?

[@sturmritter1]

What version of PyTorch are you using? I saw 2.2.0 on the screen in passing, but is +cu also included? The reason I'm asking is that I'm getting SD to run fine, with gpu recognized, but when I attempt to load a model I get an error: 20:14:51-079163 ERROR Diffusers failed loading: model=D:\stablediffusion\SDNext\automatic\models\Stable-diffusion\dreamshaper_8.safetensors pipeline=Autodetect/NoneType Building PyTorch extensions using ROCm and Windows is not supported. 20:14:51-083150 ERROR loading model=D:\stablediffusion\SDNext\automatic\models\Stable-diffusion\dreamshaper_8.safetensors pipeline=Autodetect/NoneType: OSError ┌───────────────────────────────────────── Traceback (most recent call last) I'm currently using PyTorch 2.3.0+cu118 (I'm currently using the Vladmantic folk, but this also occurs on my ishggytiger fork as well.)

[@rtchannel8171]

Thank you, Work perfectly on my Rx6800 so fast. Amazing.

[@FE-Engineer]

Fantastic! I’m glad to hear that. Thank you for watching :)

[@darkenblade986]

thanks you so much for this tutorial. this worked for me and i have an unsupported 6700xt. first time i got inpaints and sdxl working properly. you do a good job explaining things but the best is how u put the links to everything in the description. makes my life so much easier.

[@Eminic112]

what's your performance like with the 6700xt im curious

[@2ndGear]

My 6600 XT does 2/its it sucks. Shouldn't have cheaped out on a card lol.

[@Jay-js6zr]

I also have a 6700xt and am struggling to make it work, would you be able to share any issues you had while setting this up and how you overcame them please? :)

[@darkenblade986]

@@Eminic112 between 1 to 2 iters per sec it depends on the prompt. More tokens takes longer.

[@darkenblade986]

@@Jay-js6zr I just followed the guide. Wasn't to hard. Make sure you are following it to the letter.

[@terrestrialman]

thank you so much, this was actually not too bad to set up!

[@FE-Engineer]

Yea, it is not exactly straight forward, but it is not that bad either. Thank you for watching and the kind words :)

[@pastilliperse6663]

4:50 'webui.bat' is not recognized as an internal or external command, operable program or batch file.

[@FE-Engineer]

Chances are your file has something like a txt extension instead of .bat. Or the file does not exist…

[@udinmoklet]

Thank you so much bro, it's working on RX 6700 XT! took 23 mins+ on first generation

[@FE-Engineer]

You are very welcome! Thanks for watching :)

[@joris2032]

very nicee! can it generate fast now?

[@udinmoklet]

@@joris2032 well kinda fast, under 15 seconds maybe? depends on the resolution

[@joris2032]

@@udinmoklet sound okeay! I am trying to install it for my 6700xt aswell but de hip sdk isn't working for my card, im now trying an other version. 5.5.1

[@udinmoklet]

@@joris2032 there's extra steps that you have to do, read the documentation

[@KalidrethBaelric-o1c]

In case this helps anyone else... I ended up having to redo my installation. The second time I installed, I copied in AlbedoBase XL and used it for the first inference. I worked immediately without the 30 minutes of doing nothing that I got with the default model. Anyway, good luck out there everyone :)

[@taylormurphy2551]

can you please provide exact version numbers for both zluda and stable-diffusion-webui-directml? Newer versions of both have been released and I'm getting errors when I try to run webui.bat at the end of the installation process. I assume this is because I'm using incompatible versions of different packages? Thank you!

[@musaaltark.4124]

hey, did you find any solution for this? i have the same error

[@corneduplessis6337]

I appreciate your content. Its so frustrating that it cant just work for AMD on windows like it does for Nvidia cards. Im hoping that'll change in the near future but for now I use my 3070 for SD and my 7800XT for gaming and I'm good with that

[@featy2671]

do u know how much it/s i should get with a rx 7800xt if i dont all right?

[@HamguyBacon]

update* I am getting 10-57s/it using rx7800xt text to image using Stable Cascade + Zluda with over a dozen browser tabs open i created a 3840 x 2160 image, I'm using as my wallpaper with the highest around 36s/it

[@FE-Engineer]

It is not using your GPU. Did you add the -use-zluda flag?

[@fabear4022]

Noice, works. The only thing different I did from this video is downloaded the latest version of zluda. It's slow though on RX 6700 XT 12GB. I guess my card isn't as good as I thought it was. At least it freaking works.

[@FE-Engineer]

I did change to the latest version. Overall I did not honestly see any noticeable difference. But for some it might provide a more noticeable change? Or perhaps it supports more cuda functions?

[@fabear4022]

@@FE-Engineer Yes, it's about the functions. Everything I would like appears to work, as previously it would just break. And there definitely is a performance increase.

[@RimZeime]

Got it running atlast all thanks to you!!

[@Cessna-172]

Such a tutorial has been waiting for a long time. Thank you so much for your service to the Amd community, which is so hated by the AI community

[@FE-Engineer]

You are welcome. I’m glad finally on windows something with relatively decent performance that seems to not be seriously lacking in something.

[@MegaGranj]

Great tutorial! P.S For my 7900XTX perfect argumatent for SDXL, with minimum crashes(one out of ~500 generations) for 1024x1024 is: set COMMANDLINE_ARGS=--use-zluda --disable-nan-check --no-half-vae set PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True,max_split_size_mb:512

[@badis103]

👍👏

[@darthilli]

Okay, I finally got it working thank you so much, you’ve earned a sub

[@FE-Engineer]

Glad it’s up and running! Thank you for watching! :)

[@darthilli]

@@FE-Engineerkeep up the good work, so much faster now 😌

[@konstabelpiksel182]

the last time i followed your comfyui + windows with directml guide, it worked like a charm for my rx6600 for sd15. wondered if this is any faster. got myself a 4070s now tho 😁

[@FE-Engineer]

I believe this should be a decent bit faster than just directml -- if I am remembering correctly, this might be about double the performance of directml alone.

[@ajschwartz3924]

At around the 8:25 mark is where you lose me. Because I get this weird clang error message when it's compiling the package and it wont launch the webui. I'm on a 7900XT, but so far this tutorial has taken me further than all the others ever have.

[@DrivEDrivinginEurope]

hi, I have this error after launching webui.bat to install everything: rocBLAS error: Cannot read C:\Program Files\AMD\ROCm\5.7\bin\/rocblas/library/TensileLibrary.dat: No such file or directory for GPU arch : gfx1036 rocBLAS error: Could not initialize Tensile host: regex_error(error_backref): The expression contained an invalid back reference. Press any key to continue . . . Any idea what to do? Thanks for your help

[@banned-user]

same error

[@banned-user]

hey I just fixed it. disable your integrated gpu in device manager and wait a while as it loads and eventually downloads

[@DrivEDrivinginEurope]

@@banned-user thank you, I will try it later. I'm not too sure though how to disable the integrated graphics

[@FE-Engineer]

Can do it from bios for one. But you can also set it as an export variable for being used. By rocm and tell it to ignore the igpu

[@FE-Engineer]

I can tell you something is wrong. See how slashes go from back slashes to forward slashes? And at one spot there is a backslash next to a forward slash? Look at your env variables and check to see if something is weird.

[@KyleBaran90]

I'm confused. I have an AMD RX 6600. Originally I had directml going and a friend suggested I use SD Next instead. That seems to be the UI aspect of it. I did manage to get ZLUDA set up (I have no idea what it does) and everything seems to be running, including the ROCm stuff. But when I generate even a 128x128 image with 10 steps, it takes over over minutes. It seems to still be using my CPU. I have no idea why or how to change it

[@crocknroll]

this tutorial is awasome, finals the 7900xtx is usable in a1111, haleluia

[@victorivanov5667]

Hey, thanks for the ongoing amazing videos, worked like a charm the first time, but after the 2nd try I get the skip torch cuda error ; adding the --skip-torch-cuda only results in an error several people in the comments are expieriencing. EDIT: Found the solution, had to open cmd in the zluda dir then navigate to the folder with the webui.bat and start it like in the video!

[@tiago7063]

For me was that i didin't started zluda.exe or didn't open amd as admin, idk what solved

[@Klaster_1]

Thank you for the video, took me a while to figure it out, but I finally managed to get a decent generation improvement on my setup - to about 11 it/s in SD1.5 on 7900XTX. If others read this, try out the "--use-zluda" flag in stable-diffusion-webui-directml and SD.next do the patching for you and install the correct torch version - much easier this way.

[@Klaster_1]

@@matthewfuller9760 you multiply the it/s to the iteration count. That gives 2s for 20it of SD1.5 512x512 or 12s for SDXL base at 25 its 1024x1024. More if you swap models, i.e. if you run an SDXL refiner, but AFAIK that mostly depends on your SSD speed.

[@erwins_arm]

how do i install the correct torch version and get it installed into the right folder? complete newbie here and having issues

[@krizo96]

You're a blessing upon this world.

[@TheSnow.]

as a 7900 xtx owner i was getting so mad that i couldn't do any proper AI generation, bless you for your tutorials man. You are amazing, the true hero of AMD. but you should consider telling people about Compatibility with other models on the beginning of the video to be honest.

[@FE-Engineer]

That’s fair. I will try to include something at the beginning about this.

[@LighthouseLeads]

your the best. hope your family is all good

[@FE-Engineer]

Thank you so much! Family is getting there. My son has a lot of medical issues. So long road there. But thank you for asking! :)

[@afilthyweeb8684]

Damn you were not lying about that first run. I ended up at nearly 30 minutes

[@user-yingshubo]

我一直用directml，看这个真的是太棒了，非常感谢作者，我竟然配置成功了！！！

[@zygimantastauras]

Thank you very much, it generates pictures on AMD 6800 with around 5it/s

[@jony_tough]

How is rocm compared to SD Amd fork, that's been around? Sorry if mybquestion is incompetent.

[@Sbill.]

Man, this is mind boggling. I've been running SD for over a year now with a 6700XT, and I've been kicking myself for picking AMD over NVIDIA on my last upgrade. This is a game changer. Even getting something like ~3.00it/s is so much faster than I was getting before. And I'm getting hi-res fix running, which I could barely do before. This is awesome!

[@sei_asagiri]

how did you get it working on a 6700xt? HIP SDK is not compatible with the 6700xt (according to amd) and i get an error 215 every time i try to install it. Are you using CPU only or something else?

[@Sbill.]

@@sei_asagiri I was able to get the SDK installation to complete. Then I replaced the library files with the alternate library files provided at the link at the bottom of the video description. If you're getting an error when installing the SDK, I'm not sure what the cause would be.

[@sei_asagiri]

@@Sbill. I'm going to purchase a nvidia gpu to replace my amd gpu instead. amd feels like its only exclusively designed for linux people while nvidia is exclusively designed for windows people.

[@jakkard5026]

Works beautifully, thanks man!

[@banned-user]

4:48 what did you do here? I git cloned then entered the dir and typed webui.bat then it gives me an error

[@FE-Engineer]

I did not do anything special -- I was using windows command prompt -- if you are getting an error, then I think you might have a python problem...or python is not added to path...

[@banned-user]

@@FE-Engineer Yep fixed up. installed latest python version and had to go to "manage app execution aliases" settings and disable it. Thanks

[@zacharmento6551]

@@banned-userDid that get you past the "RuntimeError: Torch is not able to use GPU;"? That's what I'm getting for running webui.bat

[@banned-user]

@@zacharmento6551 I'm stuck on that part too after I run .\webui.bat -use-zluda

[@derarkserveristscheie1095]

Hi i have an amd 6800xt which is supported on the list but when i typed in "webui" in cmd to download some stuff i got this error at the end "ImportError: DLL load failed while importing onnxruntime_pybind11_state: A dynamic link library (DLL) initialization routine failed." does anyone know what i can do to fix this?

[@opensourcer1]

i have this same error with 6800

[@BanditEssex]

Hi, Great guide, - When I run the Webui --use-zluda at the very last step, I get "return torch._C._cuda_memoryStats(device)" - "RuntimeError: invalid argument to memory_allocated" anyidea, it loads the Ui, but of course any attempt to run anything fails. I'm on a 7900XTX

[@luxiland6117]

Hi thx! for the tutvideo, can u make a tut for install reforge+reactor or flux using zluda?

[@FE-Engineer]

Will take a look. I have been moving across the country and dealing with some family issues but I am looking for some new things to do so I will put it on my list.

[@artymusoke1352]

am getting this runtime error - return torch._c._cuda_memory stats runtimeerror: invalid arguement to memory_allocated. ive left it to render and "nothing is happening" as you initially said. so maybe it will work. how do i degrade to torch 118?

[@FE-Engineer]

Not sure. I haven’t seen folks in comments getting that. What’s your GPU?

[@davitmodebadze9707]

@@FE-Engineer Hey, great video. I have 6900XT and everything works, but I'm also randomly getting "NansException: A tensor with all NaNs was produced in Unet" error. --no-half, --medvram don't seem to help.

[@Vennnaya]

@@FE-Engineer Im getting this too, once i finally managed to navigate through all the steps that you skipped over in the video.

[@DanDanceMotion]

There were a lot of mess errors, but I finally succeeded Thank you!!

[@FE-Engineer]

Yea. It’s kind of crazy how many things say error and don’t matter. But it only takes one to wreck everything.

[@MRrDoctorWho]

Can u help??? What is the problem? I have an RX6750 XT, installed libraries, tried different ways, the error does not go away. Either the Stable Diffusion defines the graphics card on the gfx90c architecture "RuntimeError: invalid argument to reset_peak_memory_stats"

[@kingawesomezack]

getting same error - did you ever find a solution?

[@tippiebekfast]

i went from 14 seconds per iteration to 3 iterations per second on my 7800xt lol thanks

[@kingyizzus4108]

Thank you very much for the detailed tutorial❤, but I have a little problem which is that the Karras type samplers do not appear. Any solution? 😢

[@SvenKloevekorn]

Very nice work, thanks a lot!

[@FE-Engineer]

You are welcome! Thanks for watching!

[@electroTinky]

after running webui.bat for the first time this shows up ERROR: Could not install packages due to an OSError: [Errno 28] No space left on device. there are 900gig left on this drive. can anyone help?

[@lifekraft]

Ty so much for putting time and effort to help random people figure these things. Almost every single one of your recent video helped me navigate this new world of technology and i wouldnt even be able to try it without you. Ty infinitly

[@FE-Engineer]

You are very welcome! I am glad they helped! Thank you for watching!

[@Karambolagemusic]

RuntimeError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check. Any clues? Do I need to install another version of pytorch? If so, how? Thanks in advance!

[@limear]

Did you run "./webui.bat --use-zluda" in the terminal

[@davitmodebadze9707]

Hey thanks for the video. Managed to use Zluda on 6900XT. However I am randomly getting this error: "NansException: A tensor with all NaNs was produced in Unet. Use --disable-nan-check commandline argument to disable this check." I have tried: 1) --no-half and --no-half-vae 2) --med-vram 3) Enabling "Upcast cross attention layer to float32" 4) --disable-nan-check. Ignores errors, but instead produces black images. 5) Switching between diffrent models, including SDXL. 6) Disabling GPU overclock Does anyone have similar issues?

[@FE-Engineer]

Have you done Enable upcast cross attention layer to float32 And also -no-half-vae Together?

[@jozopako]

When installing with running user.bat file, it says error 1/2 no space left on device. I have 437GB free space.

[@dididipradoul9132]

works perfectly on 6800xt thx

[@Jay-js6zr]

Thank you for making these, however I’ve done all of the steps very closely and correctly. My AMD card wasn’t supported so I did that thing with the files, getting the Torch is not able to use GPU error. I added the skip-torch thing, then had an error saying no NVIDIA card found so took that out. I’m using zluda all the time, still not working, added the stuff to the env, still not working. I’ve also done the pip cache purge thing and deleted the venv file etc, no luck.

[@doseofjean]

i have the same error

[@Jay-js6zr]

@@doseofjeanI’ve got it working, make sure you fully install the rocm thing and i also installed the AMD driver that is usually turned off. Also make sure zluda is actually installed and in your environment variable by going to cmd and typing zluda -help

[@doseofjean]

@@Jay-js6zr how many it/s? When i installed rocm with everything enabled including the drivers I had an issue where installing the visual portion error’d out the install

[@Jay-js6zr]

I also did that thing with the rocblas files

[@TheLegendaryHacker]

OSError: [WinError 126] The specified module could not be found. Error loading "C:\Documents\Stable Diffusion\stable-diffusion-webui-directml\venv\lib\site-packages\torch\lib\cublas64_11.dll" or one of its dependencies.

[@ВалерийЯкимчук-р9о]

I have the same error

[@xedor993]

I had the same error and managed to figure it out this Step 1: Make sure you have 3.10.11 installed Step 2: do the pip cache purge Step 3: Delete the vevn folder Step 4: Open webui and let it download and install everything.

[@xedor993]

@@ВалерийЯкимчук-р9о I had the same error and managed to figure it out this Step 1: Make sure you have 3.10.11 installed Step 2: do the pip cache purge Step 3: Delete the vevn folder Step 4: Open webui and let it download and install everything.

[@ВалерийЯкимчук-р9о]

followed your instructions - it didn't work@@xedor993

[@bojanrajic]

I can't seem to get more than 1-2it. I have 7900XT and Ryzen 9 5900X, M2, 64GB RAM. AMD-Software-PRO-Edition-23.Q4-Win10-Win11-For-HIP, Python 3.10.11., Git 2.43.0 windows 1, added all the paths as instructed. Is it possible that the difference between 7900XTX and 7900XT is 10x?

[@Eminic112]

Can't be true, i've also noticed almost a 3X slowdown compared to running it in linux on my 6700 XT.

[@bojanrajic]

@@Eminic112 Everything is installed but i get 10x less iterations per second. I don't know what i am doing wrong.

[@Eminic112]

@@bojanrajic It seems to be an issue others are having as well, me included. I honestly couldn't tell you the reason, i've tried so many things and my performance isn't anywhere near where it should be. We might just have to wait for an update.

[@_TrueDesire_]

I thought Python 3.10.6 was the newest we could use? Newer breaks Torch.

[@Eminic112]

@@_TrueDesire_ I'm using 3.10.6 exactly, and i'm having the exact same issue, so i don't think that has anything to do with it.

[@MadMike626]

Hi, thanks for the tutorial! I did everything as you said but I'm getting an error "launch.py: error: unrecognized arguments: --use-zluda". My GPU is RX 7800 XT

[@kobusdowney5291]

Did you add the correct path?

[@MadMike626]

@@kobusdowney5291Yes. BTW I installed SD.Next and ZLUDA works fine, but in A1111 it doesn't for some reason.

[@queyjo]

I am having issues to be able to run sd-webui with ZLUDA. I tried to install the same torch version but I keep having to skip CUDA test and then I get: Error loading "C:\AI\stable-diffusion-webui-directml\venv\lib\site-packages\torch\lib\cublas64_11.dll" or one of its dependencies. Anyone could help please?

[@HankTTN]

rename those files from 11 to 12. it should be cublas64_12.dll for the newer stable diffusion automatic1111

[@queyjo]

@@HankTTN thanks! I ended up running a dual boot Ununtu with rocm 😇

[@HankTTN]

@@queyjo np! Nice, I’m trying to get SDNext up and working right now. How do you like the Ubuntu dual boot?

[@queyjo]

@@HankTTN pretty good! I had some issues since the only room driver to work on latest LTD Ubuntu was the rocm6.1, but it just works with pytorch rocm6.0 (until pytorch updates accordingly). Overall better performance than directml or zluda on my Windows. I boot into Ubuntu for image generation and keep windows for LLMs with LM studio.

[@HankTTN]

@@queyjo ahhh I see. That’s a good workflow and it isolates your image generation to the Ubuntu dual boot. I might try that if I can’t get sdnext working with zluda right now! Currently generating the first image that takes 10 min

[@i_Max_i]

Time to install SD again and try it with my 5700XT :D

[@i_Max_i]

Aaaand no, need RX6XXX, linux can override gfx version, but in windows i didn't found how to emulate navi2((

[@PumpedWalt]

any luck? I got a 5700xt too

[@Rich_Mr]

BTW when is your SD next with Zluda video is dropping out? Just curious and waiting for it as I use SD for my social media.

[@FE-Engineer]

Should be this weekend. Might have two. One for a semi updated guide for this one. It’s not really different just shorter since it now helps you to get the files setup properly. Probably also one on sd.next. And I might do one on comfyui. But that is still weird and very manual I believe. :-/

[@Rich_Mr]

@@FE-Engineer yes personally I hate comfy UI, it's complex to work on for me.

[@calebholst5776]

So, I've gotten through part of this. When I get to the command prompt section and I enter the github link it cloned, but when I typed in webui.bat, it was not recognized as an external command. Any suggestions?

[@FE-Engineer]

You have to change directory into the new directory it created.

[@ZeroNyte]

would there happen to be a updated version for this? tried quite a few things, and nothing seems to work, when using Zluda it uses cpu instead of gpu. and getting errors

[@FE-Engineer]

So. There is something. I haven’t been able to get the performance to be on par though. And things have changed a decent bit. I’m trying to get it up to a reasonable performance level though before I make a video about it. Plus in entirely unrelated news. Moved across the country and closing on a house in the next two weeks. So don’t have most of my servers or gear. Son has been in and out of the hospital constantly for several months. And trying to get some time with things being a bit slower in order to have the time to really put out something better if I can versus just slamming something out. I’m also frustrated I haven’t been able to put something out. I would have liked to.

[@emiliangroszczynski4676]

I'm getting an error. ERROR: Could not install packages due to an OSError: [Errno 13]

[@DiamondGeezer_27]

Every time you say “effectively” I’m taking a whiskey shot.

[@FE-Engineer]

Do I say it a lot? It’s really weird hearing myself from videos. Things I say too often is really weird for me to hear. Heh I’ll have to be careful and watch how many times I say effectively in the future. 😂 thanks for letting me know!

[@FE-Engineer]

The real question is what whiskey are you drinking? 👀

[@DiamondGeezer_27]

@@FE-Engineer We all do it bud. Only difference is you’re publishing it! Besides, I’m mostly relieved to consume content that was written by a human. 🤙🏻

[@MegaGranj]

Do you have any plans to make a similar video for ComfiUI + Zluda ?

[@FE-Engineer]

Possibly. It seems kinda sketchy as to whether it will work…and how well it might work. But I have been looking into it.

[@MegaGranj]

​@@FE-Engineer I got ~3tx/s for 1024x1024 images on xl model on 7900xtx. After one day of testing it looks stable. I did about 200 generations and got 0 crashes yet. BTW i thought i've added a comment with link on Chinese site where was a video with complete guide how to do it. Probably it was deleted by spam filter, or by you :)

[@MegaGranj]

@@FE-Engineer Let me know If you interested, we can do call in discord, and I'll show how it works now 🙃

[@ИльяАникин]

you are the best, man. still works.

[@TalsiSunstorm]

Would this work with ComfyUi as well?

[@FE-Engineer]

I don't know on that one, zluda is not complicated to integrate, but it is likely not zero work either, so I have not seen whether they support it or not.

[@TalsiSunstorm]

@@FE-Engineer Thanks. If it is/will be possible I hope you made a video about it :-)

[@avelardoblanco7324]

Hey I have a problem, I have a RX 7900 XT and I have ran through all the steps and am using the skip torch command along with zluda but I get an error saying RuntimeError: No CUDA GPUs are available It opens the webui but I cant generate anything because of the error. Any help would be appreciated 🙏

[@jeromeboyer3401]

Same error here please help

[@banned-user]

@@jeromeboyer3401 you have not installed ZLUDA properly

[@FE-Engineer]

As the other user mentioned you have missed a step or something. Didn’t install hip sdk? Didn’t get zluda setup? Didn’t copy the files? Didn’t change env? Hard to say. But you missed something.

[@avelardoblanco7324]

@@jeromeboyer3401 Hey I think i figured it out. Its currently on the step that takes really long time but i finally got it to get rid of the No CUDA GPUS are avilable. I just had to delete all of the old nvidia programs I had in Control Panel since I upgraded from an old Nvidia card to a new AMD one. Thats probably why it recognized the Nvidia and tried to search for a gpu. Hope this helps.

[@jeff6928]

Can you help with "RuntimeError: Cannot set version_counter for inference tensor" when trying to upscale image from Extras tab? Many people seem to have this issue. Thanks in advance for your help!

[@FE-Engineer]

I have not seen that one. I will see if I can reproduce it though.

[@jcdenton7914]

I never got into SD or FLux so I'm not going to keep up with what is automatic1111 or what is needed if I want to make images, upscale the res, do SD video, and basically everything.

[@bigwinboy]

Successfully installed and started SD, but failed to load the model, my python versions is 3.10.11, my Rocm versions is 5.7.1, my graphics board is 7900XTX

[@FE-Engineer]

hard to say, if you can start and run SD, and you did things in the order that I did, I don't know what the problem would be especially loading the model...might turn the machine off and on again, and retry?

[@bigwinboy]

​@@FE-Engineer Thanks, it's already working and generating images successfully, I had skipped your instructions about it taking 10-20 minutes to generate the first time, so I mistakenly thought it failed!

[@jcdenton23]

Thanks for the video. How do you start over if you mess up the steps? Is there a way to uninstall every thing and start over?

[@ИльяАникин]

could someone please explain me how almost all 6xxx or 7xxx AMD gpus support rocm including 7600 on that amd documentation but not specifically 7600xt I own

[@used003]

strangest thing - had troubles at first. then reinstalled it and got it working and it was working fine all of yesterday. booted up the computer today and i get runtimeerror again about it not being able to use the gpu with torch...

[@used003]

then i reboot - now it works again. weird lol

[@FE-Engineer]

Strange…. I have used it several times over a few weeks. I have never had any issues. I’m not sure what might be happening…

[@agx4035]

will this hip sdk fuck with my adrenalin driver for gaming ?