I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: <a target="_blank" rel="ugc" href="https://ko-fi.com/insult_to_ninjary">https://ko-fi.com/insult_to_ninjary</a>Your generosity helps me stay motivated to keep improving and to keep trying new things!At a Glance:<ul><li>Base model: Anime style (but you can experiment with other kinds!)</li><li>Use a VAE?: Yes (baked or your choice)</li><li>Clip skip: 1 or 2 (2 seems to be better, but experiment with both!)</li><li>LoRA weight: 1 - 0.7 (go lower if your images appear too noisy/busy/garbled)</li><li>Hires. fix: use non-default upscaler; denoising strength 0.5 - 0.4</li></ul>Description:Back in the early days of online AI image generation, the site Pixai had an in-house model called Anime Real that I absolutely loved. These days, it has been retired from their main model list, but it's still buried in their model marketplace somewhere. However, since it's their own proprietary model, it's not available for download and local generation. So this LoRA (made over a year ago but never shared) was my attempt to make something in a similar style that could be used more freely.To be honest, it's pretty rough, and it shows its age now. I think it does a decent enough job of replicating the style (though not exactly), but it can give garbled, smudgy results pretty often, and the anatomy is not great (especially hands and fingers), even by SD1.5 standards. But occasionally, you can get some pretty nice results (especially if you prompt to hide hands, like behind the back or something). So I figured it was worth a share, even if it's not particularly useful in this day and age.Troubleshooting:<ul><li>The biggest issue you're going to come across is problems with anatomy - hands, fingers, etc. Also you'll likely see some smudgy results that are not cleanly defined and coherent. I tried making a few different versions of this model, but these problems were persistent in each. Just try your best with all the usual fixes - different prompting, try a different base model, use a VAE, try different clip skip values, lower the LoRA weight, use adetailer, etc.</li></ul>Outro:If you make anything awesome, please consider posting them to the gallery! That goes for all of my LoRAs! 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 LoRAs, please don't hesitate to share them with me!

AnimeReal

AnimeReal.safetensors

v1.0

I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: <a href="https://ko-fi.com/insult_to_ninjary" rel="ugc noopener noreferrer nofollow" target="_blank">https://ko-fi.com/insult_to_ninjary</a>Your generosity helps me stay motivated to keep improving and to keep trying new things!At a Glance:<ul><li>Base model: Anime style (but you can experiment with other kinds!)</li><li>Use a VAE?: Yes (baked or your choice)</li><li>Clip skip: 1 or 2 (2 seems to be better, but experiment with both!)</li><li>LoRA weight: 1 - 0.7 (go lower if your images appear too noisy/busy/garbled)</li><li>Hires. fix: use non-default upscaler; denoising strength 0.5 - 0.4</li></ul>Description:Back in the early days of online AI image generation, the site Pixai had an in-house model called Anime Real that I absolutely loved. These days, it has been retired from their main model list, but it's still buried in their model marketplace somewhere. However, since it's their own proprietary model, it's not available for download and local generation. So this LoRA (made over a year ago but never shared) was my attempt to make something in a similar style that could be used more freely.To be honest, it's pretty rough, and it shows its age now. I think it does a decent enough job of replicating the style (though not exactly), but it can give garbled, smudgy results pretty often, and the anatomy is not great (especially hands and fingers), even by SD1.5 standards. But occasionally, you can get some pretty nice results (especially if you prompt to hide hands, like behind the back or something). So I figured it was worth a share, even if it's not particularly useful in this day and age.Troubleshooting:<ul><li>The biggest issue you're going to come across is problems with anatomy - hands, fingers, etc. Also you'll likely see some smudgy results that are not cleanly defined and coherent. I tried making a few different versions of this model, but these problems were persistent in each. Just try your best with all the usual fixes - different prompting, try a different base model, use a VAE, try different clip skip values, lower the LoRA weight, use adetailer, etc.</li></ul>Outro:If you make anything awesome, please consider posting them to the gallery! That goes for all of my LoRAs! 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 LoRAs, please don't hesitate to share them with me!

Files with SHA256: 71cd8427efd50864b67e9d17fba8fe46319daca022fe3e19ca04b146ad8c0575