Zeqiang Lai

implementation of One-step Diffusion with Distribution Matching Distillation

8

### Model/Pipeline/Scheduler description https://github.com/Zeqiang-Lai/OpenDMD ### Open source status - [X] The model implementation is available. - [X] The model weights are available (Only relevant if addition is not a scheduler)....

what is the purpose of delay_load for vision tower?

3

### Describe the issue https://github.com/haotian-liu/LLaVA/blob/7775b12d6b20cd69089be7a18ea02615a59621cd/llava/model/llava_arch.py#L33 Btw, I am also confused about why we can add token when loading pretrained models? https://github.com/haotian-liu/LLaVA/blob/7775b12d6b20cd69089be7a18ea02615a59621cd/llava/model/builder.py#L131 Will random embedding affect the model?

### Model/Pipeline/Scheduler description ```diff # pip install mulankit from diffusers import StableDiffusionPipeline + import mulankit pipe = StableDiffusionPipeline.from_pretrained('Lykon/dreamshaper-8') + pipe = mulankit.transform(pipe, 'mulanai/mulan-lang-adapter::sd15_aesthetic.pth') image = pipe('一只蓝色的🐶 in the 바다').images[0] ```...

Will the proposed datasets be released ?

3

1. Image Editing in the Wild (IEIW), 2. Object replacement based on SA-1B, Open Images 3. PhraseCut with LAMA 4. Web crawl.

Dear authors, I meet AttributeError: 'VisCpmBeeTokenizer' object has no attribute 'encoder' when running the following code: ```python #!/usr/bin/env python # encoding: utf-8 from diffusers import DiffusionPipeline from transformers import AutoModel...