yashvoladoddi37/kanji-diffusion-v1-5

<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. -->

LoRA text2image fine-tuning - yashvoladoddi37/kanji-diffusion-v1-5

These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were fine-tuned on the yashvoladoddi37/kanjienglish dataset. You can find some example images in the following.

[image] [image] [image] [image]

How to use

from diffusers import StableDiffusionPipeline
import torch

model_path = "yashvoladoddi37/kanji-diffusion-v1-5"
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, use_safetensors = True).to("cuda")
pipe.unet.load_attn_procs(model_path)
pipe.to("cuda")

prompt = "a Kanji meaning YouTube"
image = pipe(prompt).images[0]
image.save("youtube-kanji-v1-4.png")