YiYi Xu

- fixed the code example in README.md (issue #11) "unexpected keyword argument 'head_fusion' - reset the value for attribute `self.attentions` and `self.attention_gradients` before each forward pass so the we can...

Hi lucidrains: Thanks for your awesome work. This is not an issue about the code, I just want to ask - did you intentionally build the model this way that...

in this assert statement, the condition inside `not(...)` is actually the required condition ```python assert not (not concat_ngrams and dim_per_head == ngram_emb_dim), 'unigram head dimension must be equal to ngram...

I wrote a flax version of DDPM based on your implementation!

1

Hi lucidrains, I just wrote a flax version of DDPM based on your pytorch implementation :) [Denoising-diffusion-flax](https://github.com/yiyixuxu/denoising-diffusion-flax) (https://github.com/yiyixuxu/denoising-diffusion-flax) It’s mostly for my own education. And I learnt so much through...

updated doc for stable diffusion pipelines

3

* one doc page for each stable diffusion pipeline * added docstring examples (text2img, inpaint, img2img, upscale, depth2img)

error in pipeline_flax_stable_diffusion

4

### Describe the bug I run into this error when trying to run the flax example of dreambooth exactly as it is instructed https://github.com/huggingface/diffusers/tree/main/examples/dreambooth#running-with-flaxjax the error message is: ```python Traceback...

the `attention_head_dim` argument for `UNet2DConditionModel`

2

the `attention_head_dim` in `UNet2DConditionModel` seems to be passed down to `CrossAttnDownBlock2D` and `CrossAttnUpBlock2D` as the number of attention head, instead of the dimension of each attention head ```python from diffusers...

[draft] add core-api

1

convert this notebook to doc page https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb#scrollTo=jDk3_zhMsfPs

refactors pipelines inheriting from `StableDiffusionPipeline`

14

We have a couple of community pipelines that used `StableDiffusionPipeline` as the base class instead of `DiffusionPipeline`. Most of them are broken after we changed the signature of `StableDiffusionPipeline`. see...

add a `from_pipe` method to `DiffusionPipeline`

3

motivated by https://github.com/huggingface/diffusers/issues/6531 first, let's create a `StableDiffusionPipeline` with IP-Adapter ```python from diffusers import DiffusionPipeline, StableDiffusionSAGPipeline, MotionAdapter, PIAPipeline, UNet2DConditionModel, StableDiffusionPipeline, AnimateDiffPipeline, EulerDiscreteScheduler, DDIMScheduler from diffusers.utils import load_image, export_to_gif import torch...