Jonathan Perez

At the moment I am able to use [Canny Edge Detection](https://github.com/dakenf/diffusers.js/pull/8), [Pose Estimation and Semantic Segmentation](https://github.com/dakenf/diffusers.js/pull/11) (all in JavaScript thanks to [OpenCV.js](https://docs.opencv.org/4.x/d5/d10/tutorial_js_root.html)) in [diffusers.js](https://github.com/dakenf/diffusers.js) for the annotation (pre-processing) of images...

Not sure if I'm getting ahead of myself since some of the models that I will mention are new but I am not able to convert certain Text2Video or Img2Video...

I tried to use the `conv_sd_to_onnx.py` script to convert [thibaud's Canny ControlNet for SD 2.1](https://huggingface.co/thibaud/controlnet-sd21-canny-diffusers) to ONNX format but it did not work, specifically a shape mismatch error occurred. The...

## Problem Currently, there is a limit to the number of tokens that can be passed to the CLIP Text Encoder (usually 77 tokens) as explained [here](https://github.com/huggingface/diffusers/issues/2136). If an input...

## Description The changes include adding the Pose Estimation & Semantic Segmentation Annotator models along with the pre-processing functions required to get the ControlNet input image which is done using...

Usage Stats in Intermediate Steps

3

Hello, I saw that recently the `runtimeStatsText()` function might be deprecated and that now the usage metadata can be accessed with the `streamOptions: { include_usage: True}` in the stream request....