Update README.md

README.md

@@ -3,16 +3,25 @@ license: creativeml-openrail-m
 ---
 **The model also available at CivitAI: https://civitai.com/models/34553**
 
+Recommended models: v1.0-Q(uality)F(ix) and EXP-1
+
+Comparison:
+
+![Comparison](comparison.png)
+
+===
 AingDiffusion (read: Ah-eeng Diffusion) is a merge of a bunch of anime models. This model is capable of generating high-quality anime images.
 
 The word "aing" came from informal Sundanese; it means "I" or "My". The name represents that this model basically produces images that are relevant to my taste.
 
-## Guide to generate good images with this model
+Guide to generate good images with this model
 From my research, this model is compatible with NovelAI's animevae and pastel-mix-vae. I highly recommend pastel-mix-vae because it produces more vibrant color than animevae.
 
-I also recommend using **EasyNegative** (https://huggingface.co/datasets/gsdf/EasyNegative) for negative prompts.
+Important: Hi-res fix is a must if you want to generate high-quality and high-resolution images. For the upscaler, I highly recommend SwinIR 4x. All the samples I uploaded are using SwinIR 4x.
+
+I also recommend using EasyNegative for negative prompts.
 
-Important: Hi-res fix is a must if you want to generate high-quality and high-resolution images. For the upscaler, I highly recommend SwinIR 4x.
+Set Clip skip to 2, ENSD (eta noise seed delta) to 31337 and eta (noise multiplier) for ancestral samplers to 0.667.
 
 ## Samples generated using the model