stable-diffusion VS notebooks

*PICK\* (Updated Sep 5., 2022) Colab notebook NSFW Disabled: NOP's Stable Diffusion Colab by david. txt2img. img2img. Inpainting. Uses HuggingFace diffusers repo or DamascusGit repo.

Supposedly yes using this repo.

Parameters (using k_lms sampler): --ddim_steps 100 \ --H 768 \ --W 512 \ --scale 15 \ --n_iter 50 \ --n_samples 1 \ --seed $SEED \

📓 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.