@Dr. Furkan Gözükara , is your tutorial on controlnet same for SDXL too ? Only difference being the
@Dr. Furkan Gözükara , is your tutorial on controlnet same for SDXL too ? Only difference being the SDXL models right ?
Mwho can tell me to reinstall Windows, I run vlad sdnext, and it doesn't start, what to do
Ahow can i use controlnet in sdxl in runpod? It only installs outdated models
AI tried to update canny but it does not initialize controlonet
Dhey , relly i cant find on youtube , a updated workflow . haw to make my own videous into animation with stable diffusion , @Dr. Furkan Gözükara you made a video like 6 mounths ago , could you please point me in a updated direction , i dont need perfection i just want to create my ai video creatios , my daughters into someghing
EI wonder if we could use this amazing sdxl checkpoint to train our characters dreambooth - https://learn.thinkdiffusion.com/thinkdiffusionxl-model-draft/
ADeleted the download folder in /working, deleted cn-models in the root folder, still copied and pasted all over again, no way I can not update
MI've been looking at Lora's profiles for days, trying to find the best settings for poses and styles. I also trained two Lora's today, and in one of them, epoch 9 and epoch 10 produce completely different output with the same seed, so there are some interesting switches to hash out.
I'm curious, for either DB or Lora, what do you use to set the number of iterations of the folders? Because I see illogical iteration numbers like 12 or 16, while the number of images is 104 and similar non-round numbers. So just by taste, maybe there is a rule?
I'm curious, for either DB or Lora, what do you use to set the number of iterations of the folders? Because I see illogical iteration numbers like 12 or 16, while the number of images is 104 and similar non-round numbers. So just by taste, maybe there is a rule?
Ethis is amazing thank you for this
Every useful
Fbucketing is used during training
Fdifferent resolution images put into different buckets
Fye it is a so big ratio
Fsuggested resolutions are here :
Fthis is hard. maybe not use
Fonly you download sdxl models
Fi think try to install into C drive
Fhere auto installer tht install and download all : https://www.patreon.com/posts/for-runpod-and-84896373
FYouTubeSECourses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Turn your real video into an animation with just 1 click by using Stable Diffusion for free. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of Sta...
https://www.patreon.com/SECoursesPlaylist of Sta...
Falso you can use rerender
FYouTubeSECourses
In this video I share automatic Windows installer for ReRender A Video github repository - open source AI project. The auto installer script is here : https://www.patreon.com/posts/1-click-auto-for-89457537
Auto script is here : https://www.patreon.com/posts/1-click-auto-for-89457537
Official repo is here : https://github.com/williamyang1991...
Auto script is here : https://www.patreon.com/posts/1-click-auto-for-89457537
Official repo is here : https://github.com/williamyang1991...
Fyes you can use all. give it a try
AI felt stupid for dealing with this for hours
Fsorry i was away whole time
Acan you briefly explain why it keeps adding the controlnet extension if you delete the folder manually?
Fit is in their template
Awhat kind of models does rerender use? sd 1.5?
Fit supports all sd 1.5
FF
GWhat's the current best SDXL checkpoint for realistic photos of people?
PIs there a youtube video or something how to use this kind of caption for Lora? @Dr. Furkan Gözükara
MSdxl quality is insane, thank you for everything @Dr. Furkan Gözükara . Its 2 pm where I live and I managed to successfully create my very first high quality model. I had to tweak the learning rate at least 4 times, because it was overtraining too fast, but the final result is incredible. Thank u so much for your videos, tutorials and scripts, glad to be a patreon supporter :100_rainbow:
Bwhat learning rate did you end up with?
Bgreat news 
Bis it maybe possible to save more checkpoints if we put them in a temporary folder like we used to do with the downloaded models?
L@Dr. Furkan Gözükara is it more accurate to crop my dataset with your auto crop script compared to cropping it with photoshop?
LHow to enable bucketing?
MIn kohya here:
MI just trained a six-keyword Lora for SD 1.5 (poses). And it's nice to see that it produces results for all six keywords nicely, and just need a minimal Hires fix (0.3) for face. With AdamW8bit optimizer, with these settings (almost the same as I shared earlier, slightly modified and higher weights).
Now I'm retraining with the same parameters, but I've turned on normalization, which also gave interesting results yesterday, but as I saw, it does match the Lora to the base model. I'll be curious to see what I end up with.
Now I'm retraining with the same parameters, but I've turned on normalization, which also gave interesting results yesterday, but as I saw, it does match the Lora to the base model. I'll be curious to see what I end up with.
M
GitHub
Add EMA support. Usually it is used like this:
At the start of training, the model parameters are copied to the EMA parameters.
At each gradient update step, the EMA parameters are updated using t...
At the start of training, the model parameters are copied to the EMA parameters.
At each gradient update step, the EMA parameters are updated using t...
M2e-05
S@Dr. Furkan Gözükara do we have an up to date version of dreambooth and automatic1111 that is working yet or do i still need to train from older version?
Swas hoping to try training my first sdxl model today
BGitHub
DeepSpeed lives!
Now correctly integrated, DeepSpeed allows for training SDXL's full U-net at 8 seconds per iteration on just ~12G of VRAM. See the documentation for more information!
Features
...
Now correctly integrated, DeepSpeed allows for training SDXL's full U-net at 8 seconds per iteration on just ~12G of VRAM. See the documentation for more information!
Features
...
Sa question on lora with various checkpoints: in the previous sd1.5 era, i could train a lora on sd1.5 or anylora checkpoint and use that lora on almost any checkpoints without fail. However, loras trained on & tested ok with sdxl model doesnt seem to work at all with other checkpoints (such as realVisXL) - it generates a lot of artifacts as if overtrained. Does anyone have idea why?
Sanyone have a link to the automatic1111 sdxl auto installer for windows?