LoRA training cost Civitai Buzz. If you like my work, please consider tipping me so I can keep creating them. Reacting to my images, posting your images and using Civitai generator with my models can also help.
If you upload this LoRA to other sites please add link to this page.
Description
FAQ
Comments (12)
I'm sorry for the request, but can you make a Lora model for the character Fa from the anime RPG Fudousan? This character is very cute. Oh, I love her.
not giving me the same results even tho i'm using the same model and prompts, help?
which weight you use? you can upload your generated image to civitai so we can see the parameters
Hi i'm trying to replicate your images to test the lora but my results are different, can you help me figure out why? I posted the image here
hi, the image you posted is your result?
@andinmaro146 Yea, you can see the colors are wrong and it looks a bit blurry despite being rendered at the same resolution
@OLPhotosAI which vae you use?
@andinmaro146 None, i thought the model we're using already has a baked vae
@OLPhotosAI yes most models do but i mostly use blessed2 and not the baked one. i am not sure which vae i used in these images because it is quite old but if it is not blessed2 it may be this one: https://huggingface.co/Delcos/HD-22/blob/main/HD-22.vae.pt
@andinmaro146 Can confirm using the vae you sent has fixed it, the quality is much better and the replication looks identical. However i'm using the model that's shown in civitai, which is the bakedvae one, haven't tested the nonvae yet
So this is only tested with AnyLORA checkpoint? Are there other checkpoints that work?
it work with any anime/2.5d model
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.