update README

README.md

@@ -9,16 +9,76 @@ inference: true
 
 ---
 
-This unofficial repository hosts a diffusers-compatible float16 checkpoint of the [WDXL](https://huggingface.co/hakurei/waifu-diffusion-xl) base UNet.
+This unofficial repository hosts a diffusers-compatible float16 checkpoint of the [WDXL](https://huggingface.co/hakurei/waifu-diffusion-xl) base UNet.  
 
-Usage:
+For convenience (i.e. for use in a StableDiffusionXLPipeline) we include mirrors of other models (please adhere to their terms of usage):
+
+- [SDXL 0.9](stabilityai/stable-diffusion-xl-base-0.9)
+  - tokenizers
+  - text encoders
+  - scheduler config
+- [madebyollin's fp16 VAE](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix)
+
+## Usage (diffusers)
+
+### StableDiffusionXLPipeline
+
+Diffusers' StableDiffusionXLPipeline convention handles text encoders + UNet + VAE for you:
+
+```python
+from diffusers import StableDiffusionXLPipeline, DPMSolverMultistepScheduler
+import torch
+from torch import Generator
+
+# scheduler args documented here:
+# https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_dpmsolver_multistep.py#L98
+scheduler: DPMSolverMultistepScheduler = DPMSolverMultistepScheduler.from_pretrained(
+  'Birchlabs/waifu-diffusion-xl-unofficial',
+  subfolder='scheduler',
+  # sde-dpmsolver++ is very new. if your diffusers version doesn't have it: use 'dpmsolver++' instead.
+  algorithm_type='sde-dpmsolver++',
+  solver_order=2,
+  # solver_type='heun' may give a sharper image. Cheng Lu reckons midpoint is better.
+  solver_type='midpoint',
+  use_karras_sigmas=True,
+)
+
+pipe: StableDiffusionXLPipeline = StableDiffusionXLPipeline.from_pretrained(
+  'Birchlabs/waifu-diffusion-xl-unofficial',
+  scheduler=scheduler,
+  torch_dtype=torch.float16,
+  use_safetensors=True,
+  variant='fp16'
+)
+pipe.to("cuda")
+
+prompt = 'masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, watercolor, night, turtleneck'
+negative_prompt = 'lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name'
+
+images = pipe(
+  prompt=prompt,
+  negative_prompt=negative_prompt,
+  num_inference_steps=25,
+  guidance_scale=12.,
+  original_size=(4096, 4096),
+  target_size=(1024, 1024),
+  height=1024,
+  width=1024,
+  generator=Generator().manual_seed(45),
+).images[0]
+
+```
+
+### UNet2DConditionModel
+
+If you just want the UNet, you can load it like so:
 
 ```python
 import torch
 from diffusers import UNet2DConditionModel
 
 base_unet: UNet2DConditionModel = UNet2DConditionModel.from_pretrained(
-  unet_name,
+  'Birchlabs/waifu-diffusion-xl-unofficial',
   torch_dtype=torch.float16,
   use_safetensors=True,
   variant='fp16',
@@ -26,6 +86,10 @@ base_unet: UNet2DConditionModel = UNet2DConditionModel.from_pretrained(
 ).eval().to(torch.device('cuda'))
 ```
 
+## How it was converted
+
+I used Kohya's converter script. See [this commit](https://github.com/Birch-san/diffusers-play/commit/3f16355dd0064932d0bf356ed78676089b9e46ca), and my [previous explanation](https://huggingface.co/Birchlabs/wd-1-5-beta3-unofficial#how-wd15b3-compvis-checkpoint-was-converted) for a bit more detail on how I invoke such scripts.
+
 ### NOTE: The work here is a Work in Progress! Nothing in this repository is final.
 
 # waifu-diffusion-xl - Diffusion for Rich Weebs
@@ -59,4 +123,4 @@ This project would not have been possible without the incredible work by Stabili
 
 In order to reach us, you can join our [Discord server](https://discord.gg/touhouai).
 
-[![Discord Server](https://discordapp.com/api/guilds/930499730843250783/widget.png?style=banner2)](https://discord.gg/touhouai)
+[![Discord Server](https://discordapp.com/api/guilds/930499730843250783/widget.png?style=banner2)](https://discord.gg/touhouai)