Fan Art Summertime Saga - Fan Art

5.00 star(s) 1 Vote
Discussion Reviews (1)
phoenixman123

phoenixman123

Member
Feb 10, 2019
254
1,886
Microtom said:
The base SS Lora is that. There's a problem with it however. The Lora is trained for free on civitai AI, and they have a 10k step limit for training. The more images your dataset contains, the more steps you'll need.

Including all or most of the characters causes the training to require more than 10k steps. As it is, the current Lora is undertrained.

To solve this, we can purchase GPU time to do our training somewhere else than civitai, or train locally with a beefy GPU.

When SD3 comes out, I expect to purchase GPU time to create a new and improved lora. However, it firsts needs to come out. We also might need a sexual base checkpoint like pony diffusion or we'll waste our time. And the full tech update has to release so we have access to high resolution images.
Click to expand...
In other words, be happy with what we have now as it’s a big task to do something that we can do currently do with good results.
 
Wardonn

Wardonn

Member
Jul 21, 2017
266
3,942
Microtom said:
The base SS Lora is that. There's a problem with it however. The Lora is trained for free on civitai AI, and they have a 10k step limit for training. The more images your dataset contains, the more steps you'll need.

Including all or most of the characters causes the training to require more than 10k steps. As it is, the current Lora is undertrained.

To solve this, we can purchase GPU time to do our training somewhere else than civitai, or train locally with a beefy GPU.

When SD3 comes out, I expect to purchase GPU time to create a new and improved lora. However, it firsts needs to come out. We also might need a sexual base checkpoint like pony diffusion or we'll waste our time. And the full tech update has to release so we have access to high resolution images.
Click to expand...
Techupdate has a greater resolution, but with Upscale I will achieve quite good results. If you want to try the new better model and are interested, I would share my datasets. That took me the most work and time.

New Tech Update:

new_1.png


My upscale from old art:

upscale_1.jpeg
 
  • Like
  • Red Heart
Reactions: Aahz, mc194, wwsw2 and 10 others
M

Microtom

Well-Known Member
Sep 5, 2017
1,072
3,679
Wardonn said:
Techupdate has a greater resolution, but with Upscale I will achieve quite good results. If you want to try the new better model and are interested, I would share my datasets. That took me the most work and time.

New Tech Update:

View attachment 3698195


My upscale from old art:

View attachment 3698202
Click to expand...
Yeah sure, I'd like to see one of your lora dataset. It's true that in this example, DC's art looks much blurrier compared to your upscale. The lines however have a lighter interior in your upscale version. Here, for example:
Untitled-2.png

We can probably fix that with img2img or manually by combining the two images, or manually drawing it.
 
R

red_faced

Active Member
Jul 23, 2020
785
1,942
Microtom said:
There's a lot of new content in the tech update, and it's all in high resolution! The lora will be much better after re-training it. Of course, we need to wait for the full release, which could take many months, and hopefully SD3 will be available then. We'll probably be able to use stuff we've generated for additional content.
Click to expand...
Apparently Stability gave a release date for SD3. It should be on Huggingface on June 12th.
 
You must log in or register to reply here.
Top Bottom
5.00 star(s) 1 Vote