small changes

Author: FilippoMB

README.md

@@ -7,7 +7,7 @@ This repository is a collection of simple scripts that can be used to generate i
 To start using Stable Diffusion, you first need to create an account on [Huggin's Face](https://huggingface.co/) and generate a [token](https://huggingface.co/docs/hub/security-tokens). Afterwards, if you have access to a GPU server, you can follow the basic tutorial in the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4).
 If you don't have a GPU server to run the model, you can try out Stable Diffusion using one of the Colab notebooks below. 
 
-- Text to image [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1zjr9n60q3G8Qd87WG3ZnjDgI-D1YBCbG?usp=sharing)
+- Text to image [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1MyESLsR8D5l_EBqumwxL0eMzNmd3uqs6?usp=sharing)
 - Image to image [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1zjr9n60q3G8Qd87WG3ZnjDgI-D1YBCbG?usp=sharing)
 - Sketch to image [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1MyESLsR8D5l_EBqumwxL0eMzNmd3uqs6?usp=sharing)
 
@@ -51,8 +51,11 @@ Pytorch implementation of the diffussion model presented in [].
 **Colab notebooks**
 - Introduction to diffusers 🧨, the Hugging Face 🤗 library for diffusion models [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb)
 - Introduction to Stable Diffusion with diffusers 🧨 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_diffusion.ipynb)
-- Image2Image pipeline for Stabel Diffusion using diffusers 🧨 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patil-suraj/Notebooks/blob/master/image_2_image_using_diffusers.ipynb)
-- Denoising Diffusion Implicit Models in Tensorflow [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/keras-team/keras-io/blob/master/examples/generative/ipynb/ddim.ipynb)
+- Image2Image pipeline for Stable Diffusion [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/patil-suraj/Notebooks/blob/master/image_2_image_using_diffusers.ipynb)
+- Denoising Diffusion Implicit Models in Tensorflow/Keras [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/keras-team/keras-io/blob/master/examples/generative/ipynb/ddim.ipynb)
+- Generation of videos [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/deforum/stable-diffusion/blob/main/Deforum_Stable_Diffusion.ipynb) (you need to download the weights from [here](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original) and upload them to your Google Drive)
+
+
 
 **Blogs**
 - [What are Diffusion Models?](https://lilianweng.github.io/posts/2021-07-11-diffusion-models/#nice) introduction to Diffusion models and mathematical derivations.

diffusion_from_scratch.ipynb

@@ -234,7 +234,6 @@ def __init__(
         dim_mults=(1, 2, 4, 8),
         channels=3,
         with_time_emb=True,
-        resnet_block_groups=8,
         use_convnext=True,
         convnext_mult=2,
     ):
@@ -249,10 +248,7 @@ def __init__(
         dims = [init_dim, *map(lambda m: dim * m, dim_mults)]
         in_out = list(zip(dims[:-1], dims[1:]))
 
-        if use_convnext:
-            block_klass = partial(ConvNextBlock, mult=convnext_mult)
-        else:
-            block_klass = partial(ResnetBlock, groups=resnet_block_groups)
+        block_klass = partial(ConvNextBlock, mult=convnext_mult)
 
         # time embeddings
         if with_time_emb: