Text-to-Image
Diffusers
PyTorch
Chinese
English
StableDiffusionPipeline
stable-diffusion
diffusion-models-class
dreambooth-hackathon
wildcard
Instructions to use tilake/China-Chic-illustration with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tilake/China-Chic-illustration with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tilake/China-Chic-illustration", dtype=torch.bfloat16, device_map="cuda") prompt = "a rabbit wearing sunglasses, in the style of <guo-chao> illustration, trending on artstation, masterpiece, best quality" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Dataset Scale
#3
by AlexZheng - opened
Truly Great work!!! Can you give the number of training images or just the rough scale of the dataset?
In fact, we did two continuous finetune. For the first time, we used 200 China-Chic illustrations; The second time, we used about 80, with a smaller learning rate.
Truly Great work!!! Can you give the number of training images or just the rough scale of the dataset?
In fact, we did two continuous finetune. For the first time, we used 200 China-Chic illustrations; The second time, we used about 80, with a smaller learning rate.
Thanks! Looking forward to more work of yours.