Home Creators Posts Import Register Favorites Logout

Content

Sampling method DPM++ 2M SDE vs DPM++ 3M SDE with Schedule type Uniform vs Karras vs Exponential — I think winner is DPM++ 3M SDE Uniform — Tested on fairly overtrained DreamBooth RealVisXL V4.0 based SDXL model

I wanted to the test newest Sampling method and Schedule types

I think my new favorite is DPM++ 3M SDE Uniform

The tests are concluded on a fairly overtrained RealVisXL V4.0 based Kohya DreamBooth model

Kohya recently made some changes so my older LR values are now causing overtraining. But I wanted to see how well the model can follow my prompts even though being overtrained

Please let me know which one you think best

Not cherry picked results

40 steps and 7 CFG used

After Detailer (ADetailer) is used with 70 steps, prompt: “photo of ohwx man” , 0.5 denoise

One example full metadata (only this one has negative prompt others don’t)

muscular photo of ohwx man wearing an amazing elven steel with gold robe over it full body full pant armor in a garden in ancient rome empire, hd, hdr, uhd, 2k, 4kNegative prompt: nipples , nippleSteps: 40, Sampler: DPM++ 2M SDE, Schedule type: Uniform, CFG scale: 7, Seed: 2129378110, Size: 1024x1024, Model hash: d4ca40b15c, Model: 15_may_L2_snr_8e_6, ADetailer model: face_yolov8n.pt, ADetailer prompt: photo of ohwx man, ADetailer confidence: 0.3, ADetailer mask only top k largest: 1, ADetailer dilate erode: 4, ADetailer mask blur: 4, ADetailer denoising strength: 0.5, ADetailer inpaint only masked: True, ADetailer inpaint padding: 32, ADetailer use separate steps: True, ADetailer steps: 70, ADetailer version: 24.4.2, Version: v1.9.3

Files

Comments

Pew

"Kohya recently made some changes so my older LR values are now causing overtraining." Doc, having you in our corner is the next best thing to my being not entirely dumb. :) Do you know yet, the fix, or corrected LR value to enter into your existing (most recent) Kohya 24GB VRAM script?

The Whispering Veil

I was curious about this as well, I started having issues with the values you provided for training a dreambooth, settings that used to work just fine until I updated Kohya a few weeks ago. It would be great to see an updated settings file since things have changed a bit in the program.

Pew

Thank you! Can you please clarify as I do not know the answer. I see several entries that are similar: "learning_rate": 1e-05, "learning_rate_te": 1e-05, "learning_rate_te1": 3e-06, "learning_rate_te2": 0.0, Is it just the first line there that updates to 0.000008 (8e-6) or more than one?