Extracted LoRA Quick Test
Added 2024-07-23 00:01:09 +0000 UTCI did a test for one of our supporters. Used one of my older quite a bit overtrained DreamBooth model
Extracted LoRA as you can see yields almost perfect quality. Yes subtly changed but you can get quality with more generations
Comments
float is best. but i didnt see much difference between bf16 and float. cuda or cpu doesnt matter as long as it fits into vram.
Furkan Gözükara
2024-07-23 09:54:56 +0000 UTCnice
Furkan Gözükara
2024-07-23 09:54:25 +0000 UTCi have one question tho, in your lora extract config you use CPU for loading the models and save/load precission to float. I have a 4090 should i use instead Cuda and bf16 ?
Nedo Braun
2024-07-23 08:44:04 +0000 UTCThanx for this Information! I will check this tonight. What i did is this if my LoRA extraction is not good enough as the full fintetuned model, i create a picture with the LoRA, then send the pic to IMG2IMG, inpaint, and mask the face there AND (important) use the Full Fintetuned Modell. - The Result is incredible
Nedo Braun
2024-07-23 08:40:04 +0000 UTC
