Instructions to use johannezz/DiffSensei with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use johannezz/DiffSensei with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("johannezz/DiffSensei", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
File size: 395 Bytes
669e245 5bab284 | 1 2 3 4 5 6 7 8 9 10 11 | ---
license: mit
---
Model checkpoint of paper [DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation](https://arxiv.org/abs/2412.07589)
Please see [GitHub repo](https://github.com/jianzongwu/DiffSensei) to get the usage
Project page: https://jianzongwu.github.io/projects/diffsensei
This repo has 8bit quantized versions of Clip image generator and MLLM |