Merge branch 'main' of https://huggingface.co/yehiaserag/anime-pencil-diffusion

README.md

@@ -15,7 +15,15 @@ A dreambooth finetune of stable diffusion 1.5 model that will output stuff in an
 # Usage
 Keep the words `anime pencil concept style` towards the beginning of your prompt to invoke the finetuned style.
 
-# V3 upload in progress
+# V4 upload in progress
+I'd say wait for v5 or use earlier versions, since I'm dumb and didn't train the text encoder nor used regularization images for v4 training
+Wasted lots of electricity on v4, hope v5 is way better in terms of style
+
+## Anime-Pencil-Diffusion-V4
+Trained for 160000 steps, constant learning rate of 0.000001 on 526 images with 0 images for regularization and no text encoder training
+
+### Examples generated by the v4 model
+<img src="https://huggingface.co/yehiaserag/anime-pencil-deffusion/resolve/main/example-v4.jpg"/>
 
 ## Anime-Pencil-Diffusion-V3
 Trained for 12000 steps, constant learning rate of 0.0000005 on 80 images with 1000 images of `illustration style` for regularization

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4666d0f9b718a6ed165ce95b8aac0d3d78031b8906fdc88ca8e735af5261788c
+size 1215981833

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f8bf0c6013bc85f810cf4da564cbec940dd1e17d7185555983f8a606b2d52b
+size 3438167534

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed0cc0427bfad9d8e3ffb6b7b557bccb40e676ef97b0b27a1fff7b5b10360e3b
+size 167335346