Task
Text To Image
B
nota-ai/bk-sdm-small
Text To Image·nota-ai· 1.9K· 32
diffusers
creativeml-openrail-m
Text To Image
dataset:ChristophSchuhmann/improved_aesthetics_6.5plusarxiv:2305.15798license:creativeml-openrail-mdiffusers:StableDiffusionPipelineregion:us
BK-SDM Model Card Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient general-purpose text-to-image synthesis. This model is bulit with (i) removing several residual and attention blocks from the U-Net of Stable Diffusion v1.4 and (ii) distillation pretraining on only 0.22M LAION pairs (fewer than 0.1% of the full training set). Desp
# pull & run locally
pip install mlforge-sdk && mlforge pull nota-ai/bk-sdm-small
pip install mlforge-sdk && mlforge pull nota-ai/bk-sdm-small
Model details
Provider
nota-ai
Framework
diffusers
Size
13 GB
License
creativeml-openrail-m
Downloads
1.9K
Likes
32
Paper
arXiv:2305.15798
Updated
2023-11-17
About nota-ai/bk-sdm-small
BK-SDM Model Card Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient general-purpose text-to-image synthesis. This model is bulit with (i) removing several residual and attention blocks from the U-Net of Stable Diffusion v1.4 and (ii) distillation pretraining on only 0.22M LAION pairs (fewer than 0.1% of the full training set). Despite being trained with very limited resources, our compact model can imitate the original SDM by benefiting from transferred knowledge. - Resources for more information: Paper, GitHub, Demo.