Instructions to use Shakker-Labs/AWPortraitCN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Shakker-Labs/AWPortraitCN with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Shakker-Labs/AWPortraitCN", 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
- Local Apps
- Draw Things
- DiffusionBee
AWPortraitCN
AWPortraitCN is based on the FLUX.1-dev. It is trained on images that is more in line with the appearance and aesthetics of Chinese people. It includes many types of portraits, such as indoor and outdoor portraits, fashion, and studio photos. It has strong generalization. Compared with the original version, AWPortraitCN is more delicate and realistic in skin quality. In order to pursue a more realistic raw image effect, it can be used with the AWPortraitSR workflow.
Showcase
Trigger words
No trigger words are requireds. LoRA recommends a weight of 0.9-1.
Online Inference
You can also try this model at Shakker AI.
Acknowledgements
This model is trained by our copyrighted users DynamicWang. We release this model under permissions. The model follows flux-1-dev-non-commercial-license.
- Downloads last month
- 95