what does your dataset look like for the face? I cannot get such a clear output with my dataset
what does your dataset look like for the face? I cannot get such a clear output with my dataset
MI have already trained in clothes and style. Prodigy has worked really well for me and I now know what to look out for on Tensorboard to get a good result. I'd like to make a fairly complex conceptual Lora. It's been on hold for a few weeks, but based on the experience of the last training sessions I might start again, but there's no urgency. It will also be a NSFW Lora, partly done by others, but not on a photo basis, but with animation. We'll see how it goes. It works as a separate Lora now, the challenge here will be the balance of kneading 4-5 concepts into one.
MTo prepare a good image file, follow these steps:
- Cut out the persons using Furkan's Yolo script.
- Use CompreFace to select 25 images with a score of 0.99-1
- Use Furkan's scaling/cropping script to create 512x512, 768x768 and 1024x1024 versions.
- Train the model with Furkan's reg images, without caption.
With these you should get an absolutely good Lora.
MAnd the lesson should not be lost:
- you don't need many repetitions, 4-5 at most
- not many pictures, 20-25, but I have trained style with 10.
- the model is intelligent. From the reg pictures it knows it's a woman and from there it knows that women wear clothes or other things. So the model knows that the woman is what I'm training, so it takes her out of their environment. And because it knows the subject is a woman, it learns quickly.
- When labelling, you have to train on a model that understands labels (otherwise the model will learn what you don't want them to learn)
MReally unnecessary 10 or more repetitions. You're wasting your time if you're training Lora with lots of reps.
MThe reason I showed you the sample images is that it is possible to generate detailed images at 512x512 on SD 1.5 basis, which is faithful to the images you have loaded, without any help from Hires or Adetailer. Of course, the helpers are nice, but even the basic is good.
MAnd with an SD 1.5 Lora, you can train with almost any smaller video card at home, with up to 6-8 GB of VRAM.
MYes, CompreFace is also important if you are training with images of strangers, because if you have images with a score of less than 0.99, your model will be bad. I very rarely let you train images with a score of 0.98 (if nothing else), because then the final results will also be scored 0.9 or below on close-up images.
MAnd the script I posted last time is really good. I also trained with 64/64 weights on the Lora generating the images above. And I used it for styling as well. Just by setting d_coef I even trained SD 1.5 model with it to 768 px.
MI look at the Tensorboard and I can see on the fly, even without sample images, that the d_coef value needs to be set stronger or weaker, and how strong the resulting Lora will be.
MAnd Prodigy rewards good source images in return for results like this.
MOne more tip for CompreFace: choose a source image with both eyes visible and at least an upper body or closer face, and nothing covering the face (sunglasses, hands, whatever). And most important: whatever you want to generate. Since a person can have multiple faces (depending on age, environment), choose the image that is most typical of the person you would generate. Compare the others to that.
MThat's it, these are the tricks for a good result.
M
MClipdrop - SDXL Turbo
M"The generated images are of a fixed resolution (512x512 pix), and the model does not achieve perfect photorealism."
MGitHub
Generative Models by Stability AI. Contribute to Stability-AI/generative-models development by creating an account on GitHub.
SHi, does someone know if I can train dreambooth inpainting model in automatic1111 or kohya?
Ryour 24gb config disables xformers... isnt that super slow?
ABut will this know to center my person in the photo? It wont crop their head off?
MFurkan's script for Yolo does not cut the heads off, but cuts the people out of the picture first, so they are in focus. And the cropping script cuts out the images absolutely fine, so you don't have to worry about that, they help a lot in creating the perfect training set.
ADoes he discuss his scripts in a video by chance?
MMYouTubeSECourses
One of the most important aspect of Stable Diffusion training is the preparation of training images. In this tutorial video I will show you how to fully automatically preprocess training images with perfect zoom, crop and resize. These scripts will hugely improve your training success and accuracy.
Scripts Download Link
https://www.patreon...
Scripts Download Link
https://www.patreon...
MIf I understand you OK, it sounds like you want to switch the model used during Inpainting from the first model that generated the base image to a different, specialized model generated from Dreambooth.
If that's the case, you should be able to switch out models during Inpainting to use the other model OK.
If that's the case, you should be able to switch out models during Inpainting to use the other model OK.
S@Dr. Furkan Gözükara for the pix art the runpod script works now?
GAnyone know how to get the most recent version of dreambooth extention working on runpod with A1111?
Gnevermind I figured it out
Fit looks lower quality
Fhaha
FSDXL Turbo all you need to know about quality
By the way SDXL 20 steps vs 50 steps has 0 difference in terms of quality in like 99% of cases
By the way SDXL 20 steps vs 50 steps has 0 difference in terms of quality in like 99% of cases
Fsadly i dont know. i havent seen anywhere in documentations
Fyes slower but better quality
Fyes working
Fi recorded video editing
Fimproved gui as well
ADoes anyone know why I'm getting tons of weird malformed limbs?
AI'm using these negative prompts
bad anatomy, bad hands, three hands, three legs, bad arms, missing legs, missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate
bad anatomy, bad hands, three hands, three legs, bad arms, missing legs, missing arms, poorly drawn face, bad face, fused face, cloned face, worst face, three crus, extra crus, fused crus, worst feet, three feet, fused feet, fused thigh, three thigh, fused thigh, extra thigh, worst thigh, missing fingers, extra fingers, ugly fingers, long fingers, horn, extra eyes, huge eyes, 2girl, amputation, disconnected limbs, cartoon, cg, 3d, unreal, animate
Fsdxl 1024 x1024?
AYep
A
Fnope
Fyou are doing 2048x2048
Fmake it like 1.25 x max high res fix
Fthis is a known issue
Fmodels cant generate much higher resolution than they were trained
Fi got to sleep hopefully see you tomorrow
Aty for the help! sleep well talk tomorrow
Ehorrifying 
DIs animatediff the best option for animation or is there other options? Just wanted yo before I start
DAlso can we use sdxl trained Lora for animation which I think is using sd1. 5