notebooks VS diffusers

📓 Open the notebook for an example of how to run a batch transform job for inference.

In order to overwrite it, the package readme has some general information about it, and also there is an example in this jupyter notebook. We are doing what is necessary via the files inside sagemaker/code, which has the inference code following SageMaker requirements, and a requirements.txt, that has the necessary dependencies that will be installed when the endpoint gets created

You still haven’t explained your use-case for the model. You can look up “Open Domain QA” models. There are a lot of them, but they’re often restricted in how well they generalize and benefit from fine tuning. E.g., https://github.com/huggingface/notebooks/blob/main/longform-qa/Long_Form_Question_Answering_with_ELI5_and_Wikipedia.ipynb

(Updated Aug. 27, 2022) Colab notebook Stable Diffusion with diffusers by huggingface. GitHub repo. Video tutorial. Official Colab notebook. txt2img. Uses HuggingFace diffusers repo.

Looks like they updated the notebook 15 minutes ago. Hopefully it works now.

Basically, you can then do similar things using HuggingFace, as indeed many have (you can explore the models in their hub)[2]

[1] https://www.youtube.com/playlist?list=PLtmWHNX-gukKocXQOkQju...

[2] https://github.com/huggingface/notebooks/blob/main/examples/...

image classification: ViT, DeiT, BEiT, Swin Transformer, PoolFormer, ResNet, RegNet, ConvNeXT, Perceiver, ImageGPT, VAN. Check out the official example scripts, example notebooks.

I'm missing something about the random factor, from the sample code from https://github.com/huggingface/diffusers/blob/main/README.md

Hey people, I noticed that combining these two methods in a single forward pass increases the controllability of the generation quite a bit. I was kind of puzzled that sometimes ControlNet yielded better results than T2IAdapter for some cases, and sometimes it was the other way around, so I decided to test both at the same time, and results were quite nice. Some visuals and more motivation here: https://github.com/huggingface/diffusers/issues/5847 And it was already merged here: https://github.com/huggingface/diffusers/pull/5869

Open Parti Prompts: The better way to evaluate diffusion models (repo)

You have disabled the safety checker for by passing `safety_checker=None`. Ensure that you abide to the conditions of the Stable Diffusion license and do not expose unfiltered results in services or applications open to the public. Both the diffusers team and Hugging Face strongly recommend to keep the safety filter enabled in all public facing circumstances, disabling it only for use-cases that involve analyzing network behavior or auditing its results. For more information, please have a look at https://github.com/huggingface/diffusers/pull/254 .

For developers, TensorRT support also exists for the diffusers library via community pipelines. [1] It's limited, but if you're only supporting a subset of features, it can help.

In general, these insane speed boosts comes at the cost of bleeding edge features.

[1] https://github.com/huggingface/diffusers/blob/28e8d1f6ec82a6...

I was training sdxl UNET base model, with the diffusers library, which was going great until around step 210k when the weights suddenly turned back to their original values and stayed that way. I also tried with the ema version, which didn't change at all. I also looked at the tensor's weight values directly which confirmed my suspicions.

Merging LoRAs is essentially taking a weighted average of the LoRA adapter weights. It's more common in other UIs.

diffusers is working on a PR for it: https://github.com/huggingface/diffusers/pull/4473