BK-SDM icon indicating copy to clipboard operation
BK-SDM copied to clipboard

A Compressed Stable Diffusion for Efficient Text-to-Image Generation [ICCV'23 Demo] [ICML'23 Workshop]

Results 11 BK-SDM issues
Sort by recently updated
recently updated
newest added

Hi,thanks for your great work! I currently have an A100 GPU server that is not connected to the internet. I can configure the environment offline. **Can I replicate your work...

Hi @bokyeong1015 , thanks for your great work! I modified diffusers/train_text_to_image.py and used your fine-tuning strategy: on 212k subset of laion. But when I run the training code, **loading dataset...

pip install -U datasets This solves the issue of loading the data.

i download the stable-diffusion-v1-4 ckpt in compvis,but still have this problem, i have triied to install transformers==4.25 4.27 and so on,but didn't work, this is the error details bash scripts/kd_train_toy.sh...

@bokyeong1015 hi thanks for sharing this wonderful work , i had few queries and request 1. Can you please share ur checkpoint-45000 on one drive or google drive , i...

It's really impressive work! If I modify the architecture of your model, can I still train it? Is this model based on some pre-trained files, or is it entirely trained...

Hi, thanks for your great job!!! I want to train controlnet using bk-sdm-v2-tiny. The controlnet training code if from https://github.com/huggingface/diffusers/tree/main/examples/controlnet. But When I run the cmd like below ![image](https://github.com/user-attachments/assets/feac8782-8ef5-42d0-b63d-324c6c2689b9) I...

in the paper, you found the unimportant SD block/layer. In that case, you may not have to retrain the model (because if you erase unimportant block/layer, the performance is almost...

I use the following script to print the architecture of BK-SDM-base / SD1.4. I cannot find which block was removed. ` from diffusers import DiffusionPipeline pipe = DiffusionPipeline.from_pretrained("nota-ai/bk-sdm-base") # or...