nightdude

kanji-lora-conv

nightdude/kanji-lora-conv

kanji-lora-conv is a text-to-image model from nightdude. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.

These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were fine-tuned on the nightdude/sakana-kanji dataset. You can find some example images in the following.