IDKiro
IDKiro
This is an interesting question. If you come across any new findings in the future, I hope you'll let me know. I'm also planning on exploring this area further in...
Releasing the source code requires communication with my superior. It is also feasible to finetune the model using conventional SD training methods, and the model will still retain its ability...
I've already submitted the open source application to the company, maybe within a week.
I am very sorry that the open source application was rejected by the company. I will close the issue for the time being and reopen it if there is further...
Try this https://github.com/tianweiy/DMD2
I'd like to share my training code with the community, but I'd probably have to lose my job if I did.
If there are extra computational resources and time. For Image2Image Translation, sketch2image is next on our list, as it allows for interactive applications.
The subsequent open source program has been terminated by the Company. I'll reopen these issues if there are subsequent progress.
v0.9 only supports steps=1.
If by strength you mean STRENGTH in SDEdit-style img2img, I haven't tested it, but since v0.9 doesn't support multistep, the support for SDEdit-style img2img should be worse.