BK-SDM
BK-SDM copied to clipboard
A Compressed Stable Diffusion for Efficient Text-to-Image Generation [ICCV'23 Demo] [ICML'23 Workshop]
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.
OSError: Error no file named scheduler_config.json found in directory CompVis/stable-diffusion-v1-4
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  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...