Видео

Seems to still work, you can ask after you generated an image what is the gen id? And you will get a code, then you can say use same id just change.. and you give what to change in it . So it seems to still work for me

@@pixaroma I got with seed id, that works, but gen id create different image, like randome

Yeah i noticed that with seed you can get that image, but I manage to use gen if to get variations in same style, i just asked to keep gen id and change a hat or something, see what works for you, not always works perfectly,but it can help depends on what you need

@@pixaroma so you are saying I can add gen id to prompt and keep the style or get same face?

With the face is harder to get the same, but style should be similar. To keep a face what I do is I select everything outside the face so you change everything but the face. Just play around and see what works, like nothing is perfect since AI just see patterns and can do similar stuff but is hard to get exactly what you want, that why select region of the image can be useful

It is not perfect, I hope they can update it soon since it has been a while since the last update

I am using sdxl a lot and the control net models are not so good as v1.5 so i didn't use them too much beside canny that i use all the times, i was hoping they can improve it or sd3 comes out

@@pixaroma I noticed the same... Wasn't sure if it was just me lol

I just installed a fresh copy today and I didn't run on any problems, so maybe try again, not sure what is the problem, if you have Nvidia usually works ok

@@pixaroma i solved it , actually i was trying to install some extension , but maybe some error happened , , later on i was panicked , and then i thought carefully , and deleted some extensions , that resolved it

The voice is from VoiceAir ai, they have it from eleven labs from what i know , i got a lifetime deal a while back

if you have nvidia card I saw tutorials online that show how to install stable diffusion on linux, so I believe you can

what if you create a style yourself like if you go to edit styles in the interface and your own style, it should create a file to hold that style. So if you add it on that folder anyway the csv and you restart forge, it doesnt appear on the styles?

So I installed a fresh version of forge just to test it, so after you first install there is no styles.csv file there unless you created a style before using that brush icon under generate, and giving a title a prompt and save. But you just download that csv file directly in to webui and it appears. So on fresh install you just put the styles.csv in webui folder and restart forge and should see it in the styles.

@@pixaroma Fantastic! Thanks a lot for help, I'm new to this. It seems I used "reload ui" button instead of re-launching the program, now all styles are appearing as they should! Big thanks for help and for making this package

@@dziku2222 glad it worked :) you are welcome

Not sure what to say maybe they changed something since i made the tutorial, if that happens with every image you use i cannot find an explanation

@@pixaroma Sorry to bother, but it looks really interesting and I would like to get it running - maybe the cause of error is simple for someone far more experienced than me. I've discovered that it works normally when I'm using baseline realistic visions model that comes together with ForgeUI - but not when I'm using something generated with old SD1.5 models like abyssorangemix <- it used to work quite well for anime pictures and was very popular on civitai half a year ago. the reason I wanted to use it, is because realistic visions doesn't seem to get older loras well enough to actually generate characters - they get... well, "realistified". I would gladly use any anime replacement, as long as it works with imgToVid svd

You can check the prompt for each style when you are using it under the image generated, i tried to not include too much detail because that will make it too similar the result from one seed to other

I created one today, but I dont have too much experience with it, I will work on it on the next days discord.gg/a8ZM7Qtsqq

last update was in 5 February, we all expected more updates, not sure what happens

If you are using forge it should appear like in the video, not sure what is the cause mayne you can ask on the extension page the have a section for bugs and issues

@@pixaroma I use stable diffusion webui v1.9.3. Can SD Forge LayerDiffusion work on stable diffusion webui v1.9.3 ?

@@hicksw5687 for the forge is separate extension, try this one maybe it works for your ui github.com/layerdiffusion/LayerDiffuse as you can see in the description of this link it say that for forge is different one and give this for forge github.com/layerdiffusion/sd-forge-layerdiffuse

@@pixaroma I installed the one you mentioned instead, but the interface still didn't appear. Can this function be used to remove the background of general pictures? For example, upload a picture directly and then remove the background?

@@hicksw5687 maybe is not compatible yet, automatic1111 made an update recently, so maybe that is the cause, sorry I can not help :(

I dont, i know only how to add control net models. I was hoping the forge team will get new updates but they didnt do any updates for a while, not sure why

@@pixaroma same for me. Forge get started as a greatest UI, but stuck in 1.0 state(. Any way try new MistoLine model - its may be more accurate for such work.

Not sure what to say, what you see in video is what i got

I am not at PC to test it, so not sure

I think you need more then 6gb of vram, usually rtx cards with 8gb or more work better. I saw another comment saying that 6bb gave an error

@@pixaroma Thanks, I guess I need an upgrade. Your videos are very helpful.

I didn't find a good way, i usually just use in paint, or i make a selection of the image in Photoshop and use that in img2img to get the right character playing with denoise to be somehow similar then i blend it again back in Photoshop with masking so it fits

@@pixaroma thanks for answering so fast! Yesterday i tried the Not masked area Option you talked about and its way faster and reliable than just using the masked area for couple pics

Promo to what?

I speed up things in video but still go pretty fast usually. I have this: - CPU Intel Core i9-13900KF (3.0GHz, 36MB, LGA1700) box - GPU GIGABYTE AORUS GeForce RTX 4090 MASTER 24GB GDDR6X 384-bit- Motherboard GIGABYTE Z790 UD LGA 1700 Intel Socket LGA 1700 - 128 GB RAM Corsair Vengeance, DIMM, DDR5, 64GB (4x32gb), CL40, 5200Mhz- SSD Samsung 980 PRO, 2TB, M.2 - SSD WD Blue, 2TB, M2 2280- Case ASUS TUF Gaming GT501 White Edition, Mid-Tower, White- Cooler Procesor Corsair iCUE H150i ELITE CAPELLIX Liquid- PSU Gigabyte AORUS P1200W 80+ PLATINUM MODULAR, 1200W- Microsoft Windows 11 Pro 32-bit/64-bit English USB P2, Retail

I have set vae to automatic and works ok

You can have both installed and play around, just put it on a different folder. It has more options and extension then fooocus from what i know