DreamExplorer
over 2 years ago

srgrafoStyle - Preserving Legacy LORA

This is not my work and I don't plan to support this, just trying to preserve this LORA for the community.

Looking forward to seeing what people create with it.

Note On Example Prompts

Model: AnyPastel_HARD

VAE: Anything3, but really any can work

Used Intensity of 1.0 - I don't necessarily think this is best but I wanted to show what this LORA is doing

No cherry picked / clean ups on images, txt-to-image only (With some highrest & control net test for one).. which will show the pain I had with text / signatures (this LORA feels pretty overtrained, be careful with high intensity)

  • I do my best to not overly pollute examples with several LORA / TI's - the goal being to show this LORA off - but you will get a lot of mileage out of easynegative or other similar Anatomy fixing TI's.

  • This does play well with other LORA's but I don't show that off.

Prompting / Info

  • This LORA likes to force characters into specific positions, you can override this by lowering it's intensity or using an aggressive CONTROL NET pose influence.

  • This model really really likes to inject signatures / text when you have it at full strength, especially resolutions outside 512 / 512 - you can kill this by lowering it's intensity / in-painting.

  • I like the aesthetic this brings to images but it does take a bit of getting used to. I use similar terms in a lot of my prompts to get lighting / tones correct.

Acknowledgments / Credits

  • Credit to the original artist SrGrafo

    • I know very little about this artist

  • Original LORA author.. I have no idea - everything around this LORA has been nuked / removed.

Read more...
Download (141 MB) Download available on desktop only

Popularity

490 100

Info

Base model: SD 1.5

Latest version (v1.0): 1 File

To download these files, please visit this page from a desktop computer.

1 Version

πŸ˜₯ There are no srgrafoStyle v1.0 prompts yet!

Go ahead and upload yours!

No results

Your query returned no results – please try removing some filters or trying a different term.