Barbie Movie style
Dataset: 768*768
Trigger word: PINK
Hope any feedback from you, you can link me on discord, huggingface, github.
All train data collection are human-manual, and training cloud environment costs me much. hope your donation to support my new model. https://ko-fi.com/cecily34
If you have any questions related to the model or its samples, how to get started or just want to share your creations, feel free to join my discord:Â https://discord.gg/GgZFF3qPEB
That is my pleasure.
đ¸ Loves U.
Description
FAQ
Comments (6)
Oh nice, you did it! that was fast :)
haha....
@Cecily_cc I have a suggestion for a LoRA:
"cutaway/cross section of a ________"
That could be a castle, a house, a space ship, or a cave... I have some example images, not really the best, but ok as a start:
I have tried to use stable diffusion to make such an image, and it is very hard. I see this as a 2 separate tags:
"2d/flat" for the images where you are looking dead on, seeing only one wall of the building, maybe "orthographic"?
And 3d/perspective for the images where you see a building corner with 2 walls and then the cross section.
@luminousdragon I see your idea. I have tried to train a lora about city building, but it is poor performance, I think the architecture checkpoint is more important than lora. And the resolution should be limited by w/h percentation for decreasing Twisted. I remember there are some great architect Checkpoint in leaderboard. Maybe you can try it.
Here is a LoRA that should complement this one nicely: https://civitai.com/models/116986/barbie-lora
great.