Views
No views yet
https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5,
converted to Lucid-native safetensors.| Tag | Params | GFLOPs | Size | Source |
|---|---|---|---|---|
CompVis_LAION (default) | — | — | 3598.02 MB | https: |
1import lucid
2import lucid.models as models
3from lucid.models.weights import Stable diffusionWeights
4
5# default tag
6model = models.stable_diffusion_v1(pretrained=True)
7
8# explicit tag (enum or string)
9model = models.stable_diffusion_v1(weights=Stable diffusionWeights.CompVis_LAION)
10model = models.stable_diffusion_v1(pretrained="CompVis_LAION")
11
12# feed token ids (tokenize with the matching lucid.utils.tokenizer)
13input_ids = lucid.tensor([[101, 7592, 2088, 102]], dtype=lucid.int64)
14out = model(input_ids)
15hidden = out.last_hidden_state # (B, T, hidden_size)https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5 via
python -m tools.convert_weights Stable Diffusion --tag CompVis_LAION.
Key mapping + numerical parity verified against the source.creativeml-openrail-m — inherited from the original weights.@inproceedings{rombach2022high,
title={High-Resolution Image Synthesis with Latent Diffusion Models},
author={Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj{\"o}rn},
booktitle={CVPR},
pages={10684--10695},
year={2022}
}