ItN's Anime Merge

CHECKPOINT
Original


Updated:

I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: https://ko-fi.com/insult_to_ninjary

Your generosity helps me stay motivated to keep improving and to keep trying new things!

At a Glance:

  • Style: Anime

  • Works with LoRAs?: Yes (maybe some better than others, but generally good!)

  • VAE: vae-ft-mse-840000-ema-pruned is baked (but you can override if desired)

  • Clip skip: 1 or 2 (experiment with both!)

  • Hires. fix: use non-default upscaler; denoising strength 0.5 - 0.4

Description:

This is my first true checkpoint merge - not just merging one of my LoRAs with a specific base model. My goal for this model was to make something that worked well with LoRAs, so that I can bang out LoRA showcase images more quickly and reliably. I wanted something that would look good on its own, but also not have a very strong style so that it would play nice with LoRAs. I also wanted it to provide at least decent coherence and definition, hands/fingers, etc. (as much as SD1.5 can anyway), to cut down on how much I have to re-gen until I get something useable (or at least inpaintable).

In the end, while this is not my perfect dream merge, I do think it came out pretty well, and I'm very happy with it! Use this if you want a solid base model to test/use LoRAs, or if you just want to make pictures in an attractive but unstylized anime aesthetic. I'm hoping this will now be my new go-to when making showcase images for my enormous backlog of unpublished LoRAs!

Troubleshooting:

  • In general, the biggest issue you're going to come across is problems with anatomy - hands, fingers, etc. Occasionally, you also might get some gens that are just not quite as crisp as you wish they'd be. For an SD1.5 model, I think this one is actually pretty good at avoiding these problems more often than a lot of other models, but it's still not gonna be perfect. If you have issues, just try your best with all the usual fixes - different prompting, use a different VAE, try different clip skip values, use adetailer, etc.

Outro:

If you make anything awesome, please consider posting them to the gallery! That goes for all of my models! I really like seeing what kind of stuff you all are able to make!

If you have any questions, feel free to ask! I will try my best to help! Also, if you have any ideas for future models, please don't hesitate to share them with me!

Version Detail

SD 1.5
The OG version

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts

Describe the image you want to generate, then press Enter to send.