Tensor.Art
Create

POV cowgirl frames

LORA
Reprint


Updated:

No showcase images available, the model won't be visible to others.

9

Another frames Lora) Now it's cowgirl POV. For now options are limited, almost ecery time it will be woman on top with legs in "M" pose. I made it overfittng again, so if you want more variety - you will need to lower the weight (and maybe use a control net to get the grid).

You still can use my guide to create gifs with that Lora.

But also you can try to do this:

  1. Make a bunch of pics with low resolution

  2. Pic the one you like

  3. Copy it's seed and make it again with highres fix on with denoising str about 0.4-0.7

  4. (optional) Go to inpaint and inpaint on faces.

  5. (optional) Use ultimate sd upscale with tile size exactly like one frame

  6. (optional) Use inpaint on face and parts you don't like

You should get much less flickering. At least I've got)

Tags

2x2frames, 3x3frames (!!!strongly connected to resolution!!! 512x512 and 768x768 accordingly)

a series of images of *** (or "POV ***")

Properties

  • Resolution MUST BE 512x512 or 768x768 (you could get decent results from other resoultions which divided by 256, for example 512x768, but results will be unstable)

  • trained on perfectDeliberate, so it works the best way with that model, but could be used with other models. Lower the weight of the Lora on the img2img step. It should help to get your style back.

Enjoy, and have a peacefull day and life)

Feel free to ask any questions here in comments, or in my discord channel.

Also I am making games with AI arts. They will be free in the future, but if you want to participate in making or have an early access - you can support me on patreon)

Also my wet hair Lora was banned here, I dunno why. You can download the last version of it from my patreon for free.

Version Detail

SD 1.5
2800
1
Another frames Lora) Now it's cowgirl POV. For now options are limited, almost ecery time it will be woman on top with legs in "M" pose. I made it overfittng again, so if you want more variety - you will need to lower the weight (and maybe use a control net to get the grid). You still can use my guide to create gifs with that Lora. But also you can try to do this: Make a bunch of pics with low resolution Pic the one you like Copy it's seed and make it again with highres fix on with denoising str about 0.4-0.7 (optional) Go to inpaint and inpaint on faces. (optional) Use ultimate sd upscale with tile size exactly like one frame (optional) Use inpaint on face and parts you don't like You should get much less flickering. At least I've got) Tags 2x2frames, 3x3frames (!!!strongly connected to resolution!!! 512x512 and 768x768 accordingly) a series of images of *** (or "POV ***") Properties Resolution MUST BE 512x512 or 768x768 (you could get decent results from other resoultions which divided by 256, for example 512x768, but results will be unstable) trained on perfectDeliberate, so it works the best way with that model, but could be used with other models. Lower the weight of the Lora on the img2img step. It should help to get your style back. Enjoy, and have a peacefull day and life) Feel free to ask any questions here in comments, or in my discord channel. Also I am making games with AI arts. They will be free in the future, but if you want to participate in making or have an early access - you can support me on patreon) Also my wet hair Lora was banned here, I dunno why. You can download the last version of it from my patreon for free.

Project Permissions

Model reprinted from : no

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Comments

Related Posts

No posts yet
Describe the image you want to generate, then press Enter to send.