Update README.md

README.md

@@ -11,52 +11,50 @@ tags:
 - safetensors
 inference: true
 ---
-# **Baka-Diffusion!** 
 
+#### UNDER CONSTRUCTION!
 
-<p align="center">
+ <p align="center">
     <br>
-    <img src="https://s1.fileditch.ch/gpghnxbfNyIINXmJAJCx.png"/>
+ <img src="https://s1.fileditch.ch/gpghnxbfNyIINXmJAJCx.png" height="1024"/>
     <br>
 <p>
 
-### Model info!
-**A high quality latent diffusion model Trained on DanBooru tags!**
+# Important Announcement!
+Baka-DiffusionV2 is delayed :( I have been working on the model for weeks and have come to a dead end, There were working test versions but the quality isn't as notable as i thought it would be, It felt like a Version1.5 than a V2 so i have restarted my entire procress but eventually it will come out but I cannot pin point an exact date so please be patient!
 
----------------------------------------
-# IMPORTANT GUIDE!
-- **[Latent Space Upscaling Tutorial!](https://github.com/Hosiokaa/Latent-Space-Upscaling-Guide-)**
-- **[Latent Space Upscaling Tutorial!](https://github.com/Hosiokaa/Latent-Space-Upscaling-Guide-)**
----------------------------------------
 
-The first row of images above were generated **with** Latent space Upscaling 
+Many thanks, 
+Hosioka.
+________
+# Baka Diffusion V1
+Welcome to Baka-Diffusion a latent diffusion model Trained and Fine-Tuned on **Danbooru** tags! our models are made to output better lighting and quality it is made to use with latent upscaling via HighRes.Fix.
+It can output high quality images with just a few tags
 
-The second row of images above were generated **without** latent space upscaling 
+e.g. **_lips, chromatic aberration, 1girl with rabbit ears, pink sun hat, upper body, brown hair, black eyes, outdoors, garden, rabbit ears_**
+# Versions!
+Our models have 2 versions FP16 and FP32 from my testing FP32 can create more complex backgrounds where as for the FP16 it creates simpler backgrounds
+________
+# Usage!
+- DPM++ SDE Karras seems to be the best sampler for BakaV1
+- ClipSkip 1
+- Upscaler Latent
+- Denoise Strength (0.5~0.7)
+- below 0.5 Denoise Blocking can occur 
 
-Model is still WiP but people have been asking me for it so here it is!
-Unfortunately this is still the base mixed model a further finetuned version will come later this month!
-## Gradio
 
-We support a [Gradio](https://github.com/gradio-app/gradio) Web UI to run Baka-Diffusion!
-
-# **The model was made to use with Latent Space Upscaling in mind**
+# **The model was made to use with Latent Space Upscaling in mind** 
 *Below are some examples generated with this model!*
-
-<img src=https://s1.fileditch.ch/PYEzwEVSPbMzArMCU.png width=80% height=80%>
+<img src= width=80% height=80%>
 
 ```
-masterpiece, best quality, 1girl, eye focus, ayanami rei, long hair, light blue hair, hair between eyes, close-up, (((white background))),
-Negative prompt: lowres, (bad anatomy), text, cropped, worst quality, low quality, jpeg artifacts, signature, watermark, username, artist name, (out of frame), black and white, obese, censored, child, loli, long fingernails
-Steps: 30, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 1242942192, Size: 1024x1024, Model hash: 63c46c36, Denoising strength: 0.75, ENSD: 31337, First pass size: 512x512
 ```
 
-### IMPORTANT!
-- **[Latent Space Upscaling Tutorial!](https://github.com/Hosiokaa/Latent-Space-Upscaling-Guide-)**
-- **Current Version of the model is still a base ModelMix**
-- **HosiokaV2 will feature a fully fine-tuned Version of this model!**
+## Changelog!
+- Removed Ckpt versions   1/16/23
+- Added Diffuser weights! 1/16/23
+- Model page overhaul     1/16/23
 
-## NSFW SHOWCASE!
-- ## **[Pixiv](https://www.pixiv.net/en/users/69494031)**
 
   ## This Project would be impossible without 
 - [HaisenBerg](https://huggingface.co/haisenberguwu)