Update README.md

README.md

@@ -8,12 +8,17 @@ tags:
 - stable-diffusion
 - disco-diffusion
 - art
+- arxiv:2208.12242
 inference: true
+library_name: diffusers
 ---
 ## Paint Journey V2 is [Paint Journey V1](https://huggingface.co/FredZhang7/paint-journey-v1) fine-tuned on 768x768 oil paintings by Midjourney, Open Journey, and Disco Diffusion
 
 To apply the oil paint effect, begin the prompt with **((oil painting))**. For starters, try using a dimension of 768x768 for any subject, 512x768 for portraits, and 1152x768 for landscapes.
 
+Instead of solely fine-tuning its Unet, Paint Journey V2 focuses on fine-tuning its text encoder with a diverse range of prompts.
+This allows for a seamless blend of the oil painting style into various other types of prompts, resulting in a more natural and dynamic output.
+
 To further improve the resolution and reduce noise in generated images, especially when using the model for img2img, use [Paint Journey VAE](./paint_journey_v2.vae.pt) in combination with [Checkpoint](./paint_journey_v2.ckpt).
 As an example, a Automatic1111's WebUI user can add both of these files to the `./stable-diffusion-webui/models/Stable-diffusion` folder.
 
@@ -44,6 +49,9 @@ As an example, a Automatic1111's WebUI user can add both of these files to the `
 
 Prompts from top to bottom:
 
+<details>
+<summary> Click to expand </summary>
+
 ```
 ((oil painting)), portrait of a cute attractive model, ((round pupil)), smirk, ((beautiful eyes)), high resolution, uhd wallpaper
 Negative prompt: low-res blurry fog mutated body ((duplicate)) ((double head)) ((long neck)) ((extra eyes)) error ((extra fingers)) long face long body ((watermark)) signature
@@ -90,6 +98,8 @@ Negative prompt: low-res blurry ((fog)) watermark
 Steps: 20, Sampler: Euler, CFG scale: 7.5, Seed: 4009095562, Size: 1056x768, Model hash: 26fd2f6f, Batch size: 4, Batch pos: 0
 ```
 
+</details>
+
 ## Automatic1111's WebUI
 ```
 git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
@@ -107,7 +117,7 @@ import torch
 pipe = StableDiffusionPipeline.from_pretrained("FredZhang7/paint-journey-v2")
 pipe = pipe.to("cuda")
 
-prompt = "((oil painting)), a boat sailing, night sky, high resolution, uhd wallpaper"
+prompt = "((oil painting)), a boat sailing, night sky, high resolution, uhd, 4 k wallpaper"
 image = pipe(prompt).images[0]
 
 image.save("./result.png")