merge

Merge branch 'main' of https://huggingface.co/Vargol/PixArt-Sigma_2k_16bit

README.md

@@ -8,30 +8,26 @@ PixArt-alpha/PixArt-Sigma-XL-2-2K-MS
 with the models loaded and saved in fp16 and bf16 formats, roughly halfing their sizes.
 It can be used where download bandwith, memory or diskspace are relatively low, a T4 Colab instance for example.
 
-To use in a diffusers script you currently(15/04/2024) need to use a Source distribution of Diffusers
-and an extra 'patch' from the PixArt-Alpha's teams Sigma Github repo
+**NOTE: This Model has been converted but not successfully tested, during the memory effecient attention
+it generates 16Gb buffer, this appears break an MPS limitation, but it may also mean if requires more than 16Gb even
+with the 16 bit model**
 
-___NOTE: This Model has been converted but not successfully tested, looks like some changes to PixArt or Diffuser are needed
+The diffusers script below assumes those with more memory on none MPS GPU's have more luck running it!
 
-~~
-A simple Colab notebook can be found at https://github.com/Vargol/StableDiffusionColabs/blob/main/PixArt/PixArt_Sigma.ipynb
+a Diffusers script looks like this, **currently (25th April 2024) you need will to install diffusers from source**.
 
-a Diffusers script looks like this.
 
 ```py
 import random
 import sys
 import torch
-from diffusers import Transformer2DModel
-from scripts.diffusers_patches import pixart_sigma_init_patched_inputs, PixArtSigmaPipeline
+from diffusers from PixArtSigmaPipeline
 
-assert getattr(Transformer2DModel, '_init_patched_inputs', False), "Need to Upgrade diffusers: pip install git+https://github.com/huggingface/diffusers"
-setattr(Transformer2DModel, '_init_patched_inputs', pixart_sigma_init_patched_inputs)
 device = 'mps'
 weight_dtype = torch.bfloat16
 
 pipe = PixArtSigmaPipeline.from_pretrained(
-    "/Vargol/PixArt-Sigma_16bit",
+    "Vargol/PixArt-Sigma_2k_16bit",
     torch_dtype=weight_dtype,
     variant="fp16",
     use_safetensors=True,