@Dr. Furkan Gözükara did I get it right, you are now training with 150 repeats, 1 epoch for 13 train
@Dr. Furkan Gözükara did I get it right, you are now training with 150 repeats, 1 epoch for 13 training images and save steps instead of epochs?
Bso 150 * 13 * 1 *2 = 3900 steps?
![Digital [Starburst]](https://cdn.discordapp.com/avatars/220961909447458817/8ecbbb3132fc6e44312f3d6d2ae3df69.webp?size=40)
DI loaded the styles.csv into Automatic and have gotten some very interesting results using the updated Juggernaut 7 model. The advantage to this model is the refiner is built into the model, so you don’t need a separate refiner. The disadvantage to using the styles in Automatic is that you cannot combine styles in one image. If you select multiple styles you will get a batch for each style you choose.
DIn the Fooocus UI you can combine styles for more variety in your art. You can also use the same model by manually adding it. I personally like to select one style and generate a prompt to see the results before adding another style or switching styles. The Fooocus Masterpiece style is my favorite so far.
DCombining two styles is, in essence, a completely different style. As you add styles to a prompt you get unexpected results.
DThe caveat to combining styles is one may completely cancel out others.
DI take my images, load them into Corel Painter or Corel Paintshop Pro and adjust them, make them fit an 8.5 X 11 sheet of paper or 11 X 17 sheet for printing. I also may completely alter the image because I don’t want photographs even though I want to study photography in order to write good prompts. At the moment I borrow other people’s prompts and modify them. I don’t want to be reliant on someone else’s prompts forever though.
DIt seems that the general consensus for most AI developers is they want photographic art. That’s all well and good but they are really limiting themselves in my opinion as SD is capable of so much more.
DTrue. Not without the use of other digital art tools but the results I am seeing can’t be ignored.
D
DThat is a raw image straight from Fooocus UI using 3 styles but the prompt itself also specifies a style which overrides apparently the selected styles.
AHowdy all - I'm trying to get MagicAnimate working in Runpod, can anyone point me to a thread or discussion?
AI tried it in comfyUI local install and it just seems buggy, the nodes are anyway, and then I realized the good Dr had already put together a better implementation. I have the Gradio space working right now in a runpod
L@Dr. Furkan Gözükara , when training a SDXL model with 30 training images of a subject for a person's resemblance, after how many epochs do you expect the images to start looking like the person?
![Digital [Starburst]](https://cdn.discordapp.com/avatars/220961909447458817/8ecbbb3132fc6e44312f3d6d2ae3df69.webp?size=16)
Fit is true
Fi told foocus developer to add
Ftesting feature
Fhe ignored
Fi recorded the video
Fhopefully will be published tomorrow
Fmagic animate tutorial very detailed
Fafter 20 epochs it should start to resemable
Fmy kaggle kohya notebook works directly on google colab pro nice
Fjust made a consultation to colab pro user
A@Dr. Furkan Gözükara Any good tools to fix deformed faces, limbs and hands when creating animations?
Ai tried inpaint + Adetailer but did not work
CHello
CI need help with React. I can't seem to get my buttons for my calculator to pop up
CIts my first React project btw really new at React(like 4 days ago new)
Fi replied your message on twitter too. that photo need upscale and overal improvement
Fto further fixed
SHello. I'm currently trying to create a face lora after watching your video: https://www.youtube.com/watch?v=TpuDOsuKIBo&t=721s. The results are somewhat disappointing, possibly due to dataset issues, but it's definitely improved since I started experimenting on my own after watching the video. However, I'm wondering if cropping a person's face or full body shot from the background and turning it into a white background would be significantly beneficial? I actually feel like it's ruining the train and result looks weird right now
YouTubeSECourses
#Kohya SS web GUI DreamBooth #LoRA training full tutorial. You don't need technical knowledge to follow this tutorial. In this tutorial I have explained how to generate professional photo studio quality portrait / self images for free with Stable Diffusion training.
Our Discord server
https://bit.ly/SECoursesDiscord
If I have been of assis...
Our Discord server
https://bit.ly/SECoursesDiscord
If I have been of assis...
AI tried adetail for upscaling but no success
BWhats the best way to upscale your dataset for maximum detail?
DAny chance a group of us could try and develop code to win $700,000.00 by deciphering 4 ancient documents found near Pompeii? https://www.msn.com/en-us/news/technology/unlocking-ancient-wisdom-ai-decodes-greek-word-from-herculaneum-scrolls/ar-AA1m3ZUO?ocid=msedgntp&pc=EDGEESS&cvid=5b89fbd3e75548e799f8543b42b70568&ei=16
DThey are called the Herculaneum Scrolls, and since we are so hyped by AI and that is the key to unlocking the text it might be fun to do it even if we lose.
SHas anyone tried training a LoRA or Dreambooth using PNGs of a subject with a transparent background (essentially subject cut out and nothing behind)? I've tried with white background and backgrounds of random colors, both successful to remove associating the training with the background and focus more on the subject, however im curious if anyone has already tried this and could speak about the results
EDIT: When using ohwx man within a prompt, the random color background works quite well. However I just tried a simple "(ohwx man:1.3)" prompt and it mostly worked well however I did receive one photo that was just a purple background, so thats worth noting
EDIT: When using ohwx man within a prompt, the random color background works quite well. However I just tried a simple "(ohwx man:1.3)" prompt and it mostly worked well however I did receive one photo that was just a purple background, so thats worth noting
SFrom what I've seen online it seems .dat upscalers are the best. However I can't personally speak to this since those are not yet supported by A1111. But looking at this, https://openmodeldb.info/models/4x-FaceUpDAT it seems exceptional
Fwhat is your GPU?
FSD 1.5 is really weak. SDXL makes huge difference
Fyou shouldnt upscale your dataset that is bad
Fbut probably hd ultimate upscaler script
Fye you need to find a way to upscale with adding more details
Fprobably you have to be expert on that field
Fcurrently SDXL or SD 1.5 doesnt have transparent support feature
Fthere is a new update to multi gpu training
Ftherefore now i am doing a new training on kaggle
MI train Lora on SD 1.5 (use Realistic Vision 5.1) with absolutely great results, check back for my comments!
Shi people! any news about the course banned from udemy? it´s the course in other place? i talk whit udemy and dont lisent to me for reupload the course