xyxxmb

I want to know if you have any plans to release the pre-training model and code, just like clip model

Have you tried to fine-tune the clip model (as official Vit-B-32) in your datasets?

8

a. How the fine-tune result is？Could you provide a set of fine-tuned parameters？ b. For fine-tuning, what suggestions do you have in parameter settings or training skills?

My environment is: linux system：centos7 cuda: 10.2 torch：1.11.0 bitsandbytes：0.34.0 Then the error is： ``` import bitsandbytes as bnb ===================================BUG REPORT=================================== Welcome to bitsandbytes. For bug reports, please submit your error...

Negative prompt weight？

1

When I trying the weighted prompt, I find that the positive weight works and perfers better, but the negative works worse. Is there a way to make certain descriptions not...

How Should I solve the problem? 

I can't find the node

finetune code?

1

Will be release the finetune code?

About generate watermark in image

3

Hi, Author. There is always a certain probability that a watermark will be generated in the middle of the image when using the trained model to generate it. What is...