Finally an UI for us who are not full-time unemployed in order to master ComfyUI

I had just installed this fork and I'd definitely be interested in seeing a video of you exploring some of these built-in features further :) Some really cool stuff in here.

Holy shit. I no joke was about to go install automatic1111 since I haven't used in a year or so since I have fallen in love with instantid, but this is awesome!!! Hope it's easy to set up and use I know what I'm doing this afternoon. Thanks!

While I'll definitely be giving this a go, I've never had the issues you mention with A1111 but that's me. This Forge does come with some nice features built in and the other plus side is that settings will easily transfer across, along with a couple of extensions that aren't default. Nice one.

interesting. what i'd like to know is what makes Forge that faster ? is there any drawback to it ? is it forced non-deterministic 'x-formers' ot things like that, or is it definitely faster with the same parameters vs comfyui & A1111 ?

haha I thought A1111 just got screwed up after using it for a while. I didn't know it was from changing models, thanks!!

Hi, I have a question for you that might be a good idea for your next content. I'm new to using Automatic1111 and the file size is getting bigger, around 40GB. I'm using ControlNet and have downloaded the extension or model seg, depth, etc. for ControlNet. When I use depth and see the preview of the depth image, will it download again in the CMD section? I thought that once I had downloaded parts of ControlNet like depth, seg, etc., it wouldn't download again, but it turns out it still downloads other parts in CMD. This also applies to extensions. Is that how it works? Or will it only download the remaining parts in CMD when using depth, etc. for the first time?

@Nerdy Rodent do you know if WebUI forge works with G-Prompter i dont wanna stop using G-Prompter atm im using it with UI/UX depending on how it works with WebUI Forge i might switch to that instead

Great overview video!! I am trying to figure out where to place upscale models... do you know folder location?

Hey Mr @Nerdy Rodant where do we put the control net models? Pretty please.

I love the humor in your voice! It always gives me a good mood.

Hey NR, do you scripts your videos? Or work in sections and edit as you go?

Long time user of A1111 and ComfyUI, i'm truly impressed. You can run turbo models, generating 832x1024 in less than a second on 3090 but even better, you can crank up to 1640x2048, generate in less than 5 seconds and no VRAM implosion. I'm not sure if it's a good idea to change branch on my original a1111 though, i run forge on a new install, just symlinked my models and extension folders. Just wow 🎉

@xXxDisplayNamexXx

3 ай бұрын

I can do the same on a 3060, this is definitely the new go to WebUI for me

@DrMacabre

3 ай бұрын

@@xXxDisplayNamexXx don't remove a1111 yet, deforum and animatediff are not fully working in forge.

@PunxTV123

3 ай бұрын

@@DrMacabre what folders did you symlink?

@DrMacabre

3 ай бұрын

@@PunxTV123the whole "models", i ended up leaving a1111 extension alone as some are specific for forge like animatediff.

Hm, Photomaker doesn't seem to work at all. How did you get it to run?

Looks interesting, I hardly use a1111 these days, preferring comfyi but I will check this out

Thanks, followed the Ananconder install video first and then this and was able to install it using the full install method with no issues. I've not used Anaconda before and been using portables. Might have to do the same with ComfyUI as I'm guess it has the same pros.

any advice on how to resolve lora and adetailer slowdowns? loras can take 4x or longer to render.

Thanks for this. What's the quickest way to create a shortcut to open this, instead of typing the path? When I click directly on the .bat, I get an error. Also, oddly enough, this isn't any faster than atuo111. Running a 4080 super.

amazing! thanks for always bring nice tips and tricks nerdy!

I wanted to switch to ComfyUi. Do you still recomend using comfy when forge is released? (I have A1111 skill)

@PaulByrd1

3 ай бұрын

I use both. I would recommend diving into Comfy Ui because you can learn a lot about backend settings and control over every aspect of AI image rendering

@janmatejka646

3 ай бұрын

@@PaulByrd1 and what about speed? Thanks

Is the download file a portable file then? Can i fownload it and use it form an external SSD?

This is really nice - works way faster with my 8GB VRAM ! Thank you ! 👍👍👍

@Gh0sty.14

3 ай бұрын

Would you say it's comparable to fooocus?

@NerdyRodent

3 ай бұрын

Glad to hear it!

@lechefski

3 ай бұрын

@@NerdyRodent Hey Nerdy, how does performance compare to comfy? And do you prefer this ui over comfy atm?

I can't get the t2iadapter controlnet for style to work in this. I don't have the clipvision preprocessor and it's not automatically downloaded when I try to use it.

Your voice is so amazing , you deserve to be a movie actor

Thanks rodent. I will try it.

My Forge is missing the IP-Adapter models, the list is empty, and thus, the function doesn't work. Any idea what this could be, or how to fix it?

Thank you. Q: Is there a way yet to create video within local Vladmandic or anything local?

@NerdyRodent

3 ай бұрын

Yes, colab is a remote Linux system that can be used without a local install

How does this compare with vladmandic's SD.Next? Is it worth switching over to Forge?

what kind of program you use for symbolic link ?

@nokodemusic

2 ай бұрын

You can create symbolic links in the CMD with mklink command lines

may i know if it works with old UI themes?

I installed it and it is indeed better and faster. Only one thing I didn't realize to get: I just wanted to try "ip-Adapter" in ControlNet, but I can't find the "ip-adapter_face_id_plus" Preprocessor because - I think - it is not updated to the last version. How can I update CN to the last version? I tried to intstall CN also but it keeps disabled because there is CN already integrated. Any idea please? I already saved the ip-Adapter models in the integrated CN Models folder, but the "Preprocessor" which is "ip-adapter_face_id_plus" isn't showing up. Is it possible to download it maybe then upload it in a specific folder inside WebUI Forge folder?

@Elwaves2925

3 ай бұрын

I'm having the same issue. I hadn't thought of it not being updated but I think my Forge ControlNet version is higher than my A1111 version - I'll have to double check as they aren't the exact same extension now. I was assuming the preprocessor wasn't being picked up because it was in the wrong folder but putting it in built-in ControlNet folders didn't solve anything. Please shout up if you find a solution and I'll do the same. 🙂 BTW, there are downloads for it under one of Sebastian Kamph's latest vids.

@saranmt1

3 ай бұрын

@@Elwaves2925 having the same issue!

@Elwaves2925

3 ай бұрын

@@saranmt1 It's listed as a high priority bug on the github, so there's nothing we ca do for now. It may already be fixed if I can understand github correctly but it's not released yet. Keep checking there for an update. 🙂

@bitterjuice

Ай бұрын

u need to change .bin to .pth

Sadtalker is working in Automatic 1111 but i cant seem to make it work in Forge. It does not show in the tab

you have any video on showing how to link the auto files to forge to use it?

I hope Stability matrix adds this package.

How the hell do we keep up? LOL I'm on my 4th UI for SD in 120 days? Dizzy...🙃

@benharris144

3 ай бұрын

Crazy, isn't it? Exciting though, no doubt!

@Elwaves2925

3 ай бұрын

You don't. You find the one that works for what you want, then keep using that. You only change when something comes along with a must have feature or update you don't have. That way you only change every so often.

@worthstream

3 ай бұрын

Heh, the awesome world of state of the art software. If it makes it better, think that text generation moves even faster than image generation. A new texgen ui comes out every day, it looks like.

@birdfingers354

3 ай бұрын

Learn the skills, not the software.

@Vestu

3 ай бұрын

Just don't switch to every kew thing but rather have an interval where you update your environment, like 4 months

thanks for making this tutorial and bringing this new alternative to our attention. I was going thru their repo. It is very tempting. Will give it a bit more time to mature before forging ahead.

@AlbertoCasanova

3 ай бұрын

this repo is as functional as the original one, try it now.

@ysy69

3 ай бұрын

@@AlbertoCasanova okay

@ysy69

3 ай бұрын

@@AlbertoCasanova I need to safe hd space! Should I delete my a1111 and install Forge ?

I can't believe it!!! thank you! i have a poor RTX3050 4GB VRAM, since the last A1111, i can run the sdxl but for generating a single image it was used to take about 10 minutes. Now with this release, an image will be generated in 2 minutes!! JUST WOW!! JUST THANK YOU

@anushdsouza9632

3 ай бұрын

2 min is still too much may be sticking to comfyui

@DreamFilmVFX

3 ай бұрын

yes. depend of your hardware. maybe in your case it's better. but for my case comfyui it's pretty slow. Personally i like ComfyUi, but (for now at least) ForgeUi, gives me better performance (for my case and uses)@@anushdsouza9632

@z1mt0n1x2

3 ай бұрын

Sounds like you're generating from your CPU. I was making sd15 images with me RX570 4GB which is much older than your 3050, and it only took me 40 seconds, and that's using the DirectML version which is even slower than using CUDA.

@DreamFilmVFX

3 ай бұрын

wait.. are you talking about SDXL right? but i've now remade the calculation, it tooks 1 minute and 20 sec.. for a SDXL 1280x968 and adetailer enabled@@z1mt0n1x2

@nenadm5747

2 ай бұрын

​@@z1mt0n1x2How can I run Forge with Amd card?

Some charitable soul to teach you how to use the A1111 repository, I've done everything changing it on the web notepad and I couldn't!

Just tried your model switching example with A1111 and it worked just fine. Maybe patched or intermittent?

Well done my friend, thank you for that, I was facing like 97% and crashes on my Nvidia 1650 Ti on a Dell Laptop now I have at top 70% and runs much more faster, thank you so much

Had did you get your photomaker model to pop up

when changing model cmd crash. i have to lunch it every time i change model. any help?

What about Nsfw ?

Can this do upscaling like SD Ultimate Upscale in A1111?

Hi All - does anyone know any hacks to get this installed on a laptop supporting a non-NVIDIA GPU? Is there any kind of wrapper for CUDA extensions? Also keen to understand the req. for Python 3.10.6? Thanks!

Nice, can i link all the model that i have on Automatic 111to forge or need to paste and drop?

@leucome

3 ай бұрын

I it possible to use symlink from the files system to make the folder point to where you store your checkpoint/model and it is going to work.

Nice! thanks for the video! Does the A1111 maintainer not merge Pull Requests regarding the issues hence someone decided to fork it and fix the base?

The entitled pessimist me is whining for realizing I've done everything wrong from the start and have to uninstall everything (Auto1111, Ooba, ST, the works) and start over and learn how to use Python environments and maybe even learn how to code while I'm at it and so much hassle just to generate images, while the adult me is slapping pessimist me and telling him to quit whining and get to work, there's nothing wrong with learning something new and useful. Oh and I hit sub. Thanks Nerdy, hope you're feeling better.

THX for this, much appreciated ! I just can't get use to the spaghetti comfy-ui even if it's much better so for me this is sweet music. I have tested it a bit and surely, it's faster (running on a 4090) and the ability to use masking in controlnet is fantastic. Thanks and I hope you post some more on WebUI Forge...

i keep getting a Torch error: ERROR: Could not find a version that satisfies the requirement torch==2.1.2 (from versions: 2.2.0, 2.2.0+cu121, 2.2.1, 2.2.1+cu121) ERROR: No matching distribution found for torch==2.1.2 and then it exits.

where I put the controlnet models?

Can anyone explain how I can use photomaker to put my own face on for example a viking? I tried selecting controlnet, then upload a photo of myself and then generate but it doesn't seem to work

@thanksfernuthin

3 ай бұрын

He said you need to download the files for it and showed the video about PhotoMaker which you'd think it would tell you where to get those files but it doesn't because he runs a full install which you wouldn't do since it's already loaded. Or I'm misunderstanding something.

Holy crap, I've been using Easy Diffusion, because well it was an easy one click install, I figured my old 2080 Super was the reason for how slow it was, This runs circles around it. 2 to 3 minute single image generations, are now completing in like 20 to 30 seconds. And my GPU now actually sounds like it's cranking into high gear when I run it. And it doesn't absolutely hog my VRAM. This is such an upgrade.

Hey i've spent about 4 hours trying to get PhotoMaker to work but just cant seem to get it working. It doesn't seem to do anything to my image even when I include the photomaker prompt. I Cant seem to find where the clip vision (photomaker) file is in the folder and I'm guessing could be a problem... anyone been able to get it working?

@zentrans

2 ай бұрын

same here

did any one else have control net inpaint model not work. the model doesnt load and can use inpaint feature. how can fix?

I like your sense of humour, great video :-) I'm getting roughly a 50% speed boost on my RTX 3070

Regular A1111 had issues. VRam spiking and crashing the program and parts of old model retained. This Forge variant controls the memory much better, with no more spikes and no more crashes. The previous model is now completely cleared and there is indeed a speed improvement, in my case of around 20 percent, making it slightly faster than even Comfy now. I'm very happy with Forge.

Help please, why Lore don`y working at this version, it`s generate fast and good, but Lore don`t working, in version which crashed but rarely gif me art all Lore was working

Anyone managed to make sadtalker work? Mine is fine in 1111 but does not show in the tab in Forge

installed fine and ran in img2img but text2img gives TypeError: 'NoneType' object is not iterable.. any ideas appreciated.. I'm running on AMD GPU

@Elwaves2925

3 ай бұрын

For me, I had the parameters for filenames wrong in the settings for image saving. If you've altered it you might want to check that.

@nenadm5747

3 ай бұрын

@sparks1943 Can you tell me what I have to do to make it work on my Amd gpu? Thank you 😊

@sparks1943

3 ай бұрын

I could not get it to work on AMD in the end I reinstalled the Ishqqytiger version and reinstall torch-directml with pip@@nenadm5747

On my tests (8gb 3070) I get images almost twice as fast as with normal a1111, but one thing confuses me: Everything the same I still get different images than in a1111, even if the github says there shouldnt be a difference.

@Fikri0o0

3 ай бұрын

are u sure u using the same settings and seed?

WOW! ....very cool! I share your enthusiasm!

After switching to Forge UI, I can't activate "ReActor". Is this still an issue? Any leads fellas?

i can't load SDXL, When i tried to load SDXL it's says just " Press any key to continue . .."

I stopped using A1111 for ComfyUI, there are some things that I go back to use it for, but I've gotten used to the speed of ComfyUI - I'll definintely give Forge a go.

What's the simplest way to create animated video from an image? I want eye blinking, but Pixverse is too warpy, random and uncontrollable.

Can use install reactor as well?

Been testing a bunch of UIs and Forge is the real deal, really polished.

Looks great, is there a CoLab notebook for it?

@preecefirefox

3 ай бұрын

Never mind, only took 10 mins to make one

I tried this a few days ago but directml support is minimal atm and hi-res fix renders were over an hour.

Can't get LORA's to load with Forge... anyone have this issue?

Actually huge thanks to video maker, Installed this webui Forge and it is indeed AMAZING!! Simply marvelous!

it's possible to run it on Amazon Sagemaker lab?

I've been waiting for masks for IP Adapter.. nice find!

Been using it for a few days now and I'm completely converted.

I have a 4gb vram gpu, does it work with forge?

Somehow cant find how to integrate LM Studio with WebUI. It's hard to create nice prompts, so expecting language models can create :)

Spmeone know why Lore not working in this version?

3:12 As a very savvy tech user who works on AI, writes GPU shaders as his day job, and is already very familiar with this ML ecosystem held up by sticks and glue, for the love of my time, I greatly appreciate installations that are just a few clicks - I have things to do.

Good stuff, did some fast testing and on mine 1070 I went from ~1.1it/s to ~1.4it/s and in HiresFix from ~6.5s/it to ~5.5s/it (working on 512x768 HiresX2 1024x1536). ~27% and ~15% performance boost vs VladDiffusion, impressive I will update Vlad to latest version and check if Forge advantage still holds, and probably switch. I just couldn't find Model/loras paths settings so I guess if I want to use it with Vlad as backup I will have to copy all models/loras to Forge and change paths in Vlad.

Excellent! Thank you.

For some reason I can't get any controlnets to work at all. Models are in the right folder but nothing happens

@Voxxx69

3 ай бұрын

Same, I've tested openpose and inpaint+lama and the don't work

@Gh0sty.14

3 ай бұрын

@@Voxxx69 Not sure if you figured it out but for me the issue was the preprocessors hadn't been downloaded. I tried using them again and this time it automatically downloaded them and then everything worked. Not sure why it didn't do that the first time.

What about AnimateDiff + Controlnet via Forge Webui?

How to run instant-ID in forge?????

Doesnt work for me. I get an error saying torch is not able to use gpu

Is WebUI Forge missing anything that A1111 has? Is it updated as often as A1111?

@Elwaves2925

3 ай бұрын

Forge has more from a fresh install because it comes with several extensions built-in. No idea how often it's updated because I think it's new but I'm not certain.

@dennishmiller

3 ай бұрын

Deforum, for one.

@xXxDisplayNamexXx

3 ай бұрын

I personally can't find a folder to hold any of the extra upscaler models, so you're stuck with the defaults

@Elwaves2925

3 ай бұрын

@@xXxDisplayNamexXx By extra do you mean upscalers you've downloaded yourself? If yes, I put mine in the 'Forge\webui\models\ESRGAN folder

so i can copy and paste my automatic stuff and it will be fine?

@deagzzzshorts

3 ай бұрын

some extensions don't work as its based of dev build

can i doi this with a macbookpro and runpod gpu?

@NerdyRodent

2 ай бұрын

If you want to use Linux via run pod, then it doesn’t matter what your local operating system is 😉

Does Forge fix the problem with Gradio's painting component being so limited you can't even erase from a mask?

Downloaded it last night(17/02/24), this one is going to replace ALL my other tools, I'm running a modest setup and this thing is blazingly fast!!(20 images in approximately 10 minutes)

I personally never had problems with changing models in A1111, is it only with SDXL models?

@Elwaves2925

3 ай бұрын

I haven't either and that's with 1.5 and SDXL models. I constantly switch between Realistic Vision and RealVisXL while keeping the same prompt.

@jdesanti76

3 ай бұрын

x2

@thebonuslvl7181

3 ай бұрын

neither did i but i understand what he's saying with that with each change it didnt release your ram, thereby stacking up and making things slower. I watch vids on my second screen and they stutter on my 4070ti while i generate images on A1111, this isn't an issue with comfyui or now Forge for me which is much more user friendly than comfyui and was the main reason i still used A1111..

Cracking video. Thanks!

@NerdyRodent

2 ай бұрын

Glad you enjoyed it

Love it, can finally run SXDL in webUI with my 8GB card.. and agreed no blasted memory issues

You talk about photomaker being built in but I don't see it in your UI or mine?

@Elwaves2925

3 ай бұрын

It's in the ControlNet section.

@Avalon19511

3 ай бұрын

@@Elwaves2925 found it thank you

@Elwaves2925

3 ай бұрын

@@Avalon19511 Great.

@twelvyvisionz7637

3 ай бұрын

@@Elwaves2925 I downloaded the Photomaker model and put it in Controlnet folder, I dont see it after refreshing the control net extention on the dropdown list tho

@Elwaves2925

3 ай бұрын

@@twelvyvisionz7637 What's the model called? Maybe I can look for it on my end. I haven't tried Photomaker in Forge yet, I prefer ReActor but I know IPAdaptor also has that problem of not showing in the list, so maybe it's the same for Photomaker? From what I've read on the github, the fixes are there and awaiting release.

Is there a code link for Kaggle?

How much space does this need? I think I can't install it because I don't have enough space?

@NerdyRodent

3 ай бұрын

It's best to have at least 20GB free

@atlas_19

3 ай бұрын

@@NerdyRodent I have 200 and it says not enough memory. What gives? Is it perhaps about the conda environment? Or perhaps could it be trying to install it on the wrong disk?

It's insane how much better it is compared to A1111, I went from 1 Minute for 1 High-Res Picture to 1 Minute to 5 High-Res Pictures.

Finally an SD UI that doesn't crash every 5 minutes what a time to be alive.

Hellp... do you have a discord or something and can help me? I was running instantid all day no problems went to install this and now no python projects will connect to huggingface I get a 443 timeout on installing clip and ever since that happened I can't connect any projects to huggingface model downloads... I'm baffled . Reinstalled python and still timing out on all downloads.

@Elwaves2925

3 ай бұрын

Hugging Face was down for a bit for maintenance. You didn't need to reinstall anything. Always check the site in a browser first.

Does this have dreambooth?