Edit model card

BK-SDM-2M Model Card

BK-SDM-{Base-2M, Small-2M, Tiny-2M} are pretrained with 10× more data (2.3M LAION image-text pairs) compared to our previous release.

  • Block-removed Knowledge-distilled Stable Diffusion Model (BK-SDM) is an architecturally compressed SDM for efficient text-to-image synthesis.
  • The previous BK-SDM-{Base, Small, Tiny} were obtained via distillation pretraining on 0.22M LAION pairs.
  • Resources for more information: Paper, GitHub, Demo.

Examples with 🤗Diffusers library.

An inference code with the default PNDM scheduler and 50 denoising steps is as follows.

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained("nota-ai/bk-sdm-small-2m", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "a black vase holding a bouquet of roses"
image = pipe(prompt).images[0]  

Compression Method

Adhering to the U-Net architecture and distillation pretraining of BK-SDM, the difference in BK-SDM-2M is a 10× increase in the number of training pairs.

  • Training Data: 2,256,472 image-text pairs (i.e., 2.3M pairs) from LAION-Aesthetics V2 6.25+.
  • Hardware: A single NVIDIA A100 80GB GPU
  • Gradient Accumulations: 4
  • Batch: 256 (=4×64)
  • Optimizer: AdamW
  • Learning Rate: a constant learning rate of 5e-5 for 50K-iteration pretraining

Experimental Results

The following table shows the zero-shot results on 30K samples from the MS-COCO validation split. After generating 512×512 images with the PNDM scheduler and 25 denoising steps, we downsampled them to 256×256 for evaluating generation scores.

  • Our models were drawn at the 50K-th training iteration.
Model FID↓ IS↑ CLIP Score↑
# Params,
# Params,
Whole SDM
Stable Diffusion v1.4 13.05 36.76 0.2958 0.86B 1.04B
BK-SDM-Base (Ours) 15.76 33.79 0.2878 0.58B 0.76B
BK-SDM-Base-2M (Ours) 14.81 34.17 0.2883 0.58B 0.76B
BK-SDM-Small (Ours) 16.98 31.68 0.2677 0.49B 0.66B
BK-SDM-Small-2M (Ours) 17.05 33.10 0.2734 0.49B 0.66B
BK-SDM-Tiny (Ours) 17.12 30.09 0.2653 0.33B 0.50B
BK-SDM-Tiny-2M (Ours) 17.53 31.32 0.2690 0.33B 0.50B

Effect of Different Data Sizes for Training BK-SDM-Small

Increasing the number of training pairs improves the IS and CLIP scores over training progress. The MS-COCO 256×256 30K benchmark was used for evaluation.

Training progress with different data sizes

Furthermore, with the growth in data volume, visual results become more favorable (e.g., better image-text alignment and clear distinction among objects).

Visual results with different data sizes

Additional Visual Examples

additional visual examples


Follow the usage guidelines of Stable Diffusion v1.



  title={BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion},
  author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
  journal={arXiv preprint arXiv:2305.15798},
  title={BK-SDM: Architecturally Compressed Stable Diffusion for Efficient Text-to-Image Generation},
  author={Kim, Bo-Kyeong and Song, Hyoung-Kyu and Castells, Thibault and Choi, Shinkook},
  journal={ICML Workshop on Efficient Systems for Foundation Models (ES-FoMo)},

This model card was written by Bo-Kyeong Kim and is based on the Stable Diffusion v1 model card.

Downloads last month