Видео

Control net not working fine

Ive got error torch cuda

Thanks for the video! aspect ratios were removed from config.txt in new Fooocus update. They are now in config_modification_tutorial.txt

Can I use comfy ui with 4gb nvidia vram

@2:10 - you can press winkey+e for opening explorer ;)

What he doesn't mention. Don't use it if you are on anything except a Nvidia card. Radeon cards will have to run --directml but will probably have issues.

I am using rtx2060, and Forge solves some speed problems when i try to use SDXL models... Its much much faster.. When i use 111 it can take 30-1hr for 1 render... vs Forge which might take 5-10min or lesser. The good thing is that i have both installed.. and they both share the models.. so if i really need i can just switch back to Automatic1111 ... so far i have not really needed to do that..

saw this in my feed, I do Stable Diffusion Videos. I found an epic flaw with Forge. It can't generate images with wide aspect ratios but Automatic1111 can.

Dicoba tapi tak bisa jalan

When you try to generate a video of walter white but forget to use control net

hi is there a way to get dark mode with forge i have it with automatic 1111

Can I run it on Intel HD Graphics?

Issues occur with FORGE when updating Pytorch and CUDA. For FORGE you need to do a downgrade.

What does this give us that Fooocus doesn't?

Actually, it'll run on 2GB also at about 10s/iteration. It helps immensely that it supports SD 1.5 models, of which there are many pruned versions that can be loaded almost entirely into the GPU.

Dark Mode sir!

What would you suggest, change both of my DP to DP cables to the same one but active? I'm also wondering why you are using a VGA connector and not DP?

Hi. I bought the exact same video card as yours a couple days ago and now I'm having similar problems. I have 2 FullHD monitors that I have been using for a long time without any problems, using the IGPU from Ryzen 9. To clarify, my main monitor was connected via DP-DP and the other via HDMI-HDMI. After buying a video card, I connected both via DP. The thing is that I don't notice such problems in the game, but only when watching RUclips or movies. I checked the GPU with different tests, rendered the scene in V-Ray and everything went well. But when it comes to video I see that the picture is not smooth and some frames are skipped.

RuntimeError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check

any suggestion for sdxl? for now it takes about 5 min for one photo

all gpus? 4gb? now my rx 580 can do something

Jesse we need to cook

Thanks. I've never used a "detailer."

using windows, sorry would done vote but the tutorial is good so...

Thanks! Best video on installation and also on a version that will work on my old card.

Fewer resources - for god's sake.

Walter white ?

Thanks, is impresive fast. how i can add or change the woman face factions i mean for example from a picture? thanks

Thank you for this. I had been pulling my hair out all day trying to get SD installed follwing another persons guide (think it may have been outdated), having all sorts of errors with pytorch installations and webui batch load issue. Eventually found your video and I was installed in a matter of minutes :)

Your video feed, the talking head portion, is overly processed and sharpened. It's quite uncanny, maybe there's a way to tone it down?

thanks heisenberg 🧑‍🍳

forge starts extremely slowly for me or not creating images at all is painfully slow. I have a gtx1080ti with 11gb and fooocus and comfy work great

Is there a code link for Kaggle?

you look like you were ai generated

It might be faster, not better. The quality is really poor next to a1111, at least when it comes to img2img and batch sequencing. I’m very disappointed…..same model, same seed, same everything and still getting completely different results…..same as comfy…..

Any way to get wildcards to work on forge? My extensions has it listed but doesnt actually show the tab on the front UI

Yes, i can confirm that it works great with gtx1050ti 4gb. But my other pc is ryzen7735 with dedicated 4gb vram and no chance getting it to work.

Great, Thank you.

No Linux tho sad

"Automatic1111, also known as Stable Diffusion WebUI, is a free and user-friendly GUI for advanced users of Stable Diffusion.1 It is a powerful tool that revolutionizes the way we create AI-generated images with its efficient and stable diffusion process, providing accurate and high-quality results.2 However, it is not the easiest software to use due to lack of documentation.1 The actual name of the software is webui, but it is commonly referred to as Automatic1111" Mmm.

Like always, just for Nvidia. So the "all GPU's" mean all Nvidia GPU's. Come on AMD pick up the slack, I also want to play with this.

I am using Cascade from stable diffusion on rtx 3060. No issues. My whole computer was about 755 dolars. excluding the monitor which i got for about 15 dollars (22 inches samsung). on top of that you need a mouse keyboard and speakers. all of that under 800 $. Stable diffusion does all i want. Just some info for those who might think they neeed a ton of money to join the fun.

Ayy that's awesome news 💯💯

plaese use a decent mic

I wonder if free speech forks of SD can be made?

This is why I disagree that whoever gets AGI first will have an impossible advantage over the rest towards ASI. I think, yes, someone has to get it first, but within a week, several others will announce AGI. One of the consequences of an exponential rate of progress, is that developments occur more closely bunched together since so many are happening and progress is quickly replicated. So I think it very likely we could have SEVERAL initiatives achieve even ASI when it happens, which of course will be amazing for what happens next: do they start chatting and start to simply work together to sum their strengths???

I don't think Stable diffusion will become a commercial product, the reason why is weights are easy to distribute, and not even clearly covered by copyright law. The licenses they are distributed under today are probably not enforceable. I suspect gen AI is going to gut IP, which I'm all for. If it does not gut IP, the result is going to be partial ownership of everything by megacorps creating models, or by states taxing everyone using things in order to fund harebrained schemes for basic income, which won't work because we need lots of dirty jobs done to produce energy, unclog plumbing, etc. Does anyone think people taking on all those dirty jobs are going to be fine paying a bunch of artists or programmers who think they can't work anymore? I very much doubt it. Incentives prevent basic income from making sense, so this is all extremely unworkable. Many of us programmers and artists will need to find something we can do that is valuable to other people. And there's a lot to be done people want done that they don't get today, maybe not work we want to do, but we'll probably have the time. *Of course, those working with the AI and upskilling themselves regularly will fair better, but this requires more than just the basic levels of creativity that many apply, so it's going to be rough for the mid level people or anyone remotely inflexible.

Censored outweighs all pro rendering it effectively useless. For example I asked Gemini just yesterday "generate a photo of a white rabbit". Instead of getting a photo of any kind it wrote two paragraphs about how racist it was to ask it to make the rabbit white.

🎯 Key Takeaways for quick navigation: 00:04 *🚀 Introduction to Stable Diffusion 3 features* - Stable Diffusion 3 incorporates the Diffusion Transformer architecture, similar to OpenAI's Sora, promising significant advancements. - Major features include 3D image and video generation, enhanced text generation, and styling capabilities, making it a highly anticipated release. - It aims to rival top AI models like Dahl-e and Sora, offering versatility and performance improvements. 01:27 *📈 Stable Diffusion 3's potential performance* - Stable Diffusion 3's enhancements position it to potentially outperform competitors like Dahl-e and MidJourney. - It aims to address hardware limitations by offering variations of the software for lower-spec GPUs, expanding accessibility. - The announcement of Stable Diffusion 3 follows OpenAI's success with Sora, indicating a competitive response. 03:12 *💻 Concerns and improvements in Stable Diffusion 3* - Notable improvements in Stable Diffusion 3 include better text rendering, 3D image generation, and AI's ability to distinguish between elements in an image. - There are concerns within the community regarding potential censorship in Stable Diffusion 3, which could limit creative freedom. - Speculation arises about Stable Diffusion eventually transitioning to a paid product, highlighting the importance of utilizing it while it's free. 06:19 *🔒 Future outlook and conclusion* - Users are encouraged to capitalize on Stable Diffusion's free availability to master its capabilities before potential paid versions are introduced. - Stable Diffusion 3 promises significant improvements despite potential challenges like hardware requirements and censorship concerns. - The release of Stable Diffusion 3 is eagerly anticipated, with users looking forward to exploring its enhanced features. Made with HARPA AI

Nice video, super excited about Stable Diffusion 3!!!