Instructions to use NO8D/ExpressionControl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use NO8D/ExpressionControl with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.2-klein-9B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("NO8D/ExpressionControl") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| tags: | |
| - text-to-image | |
| - lora | |
| - diffusers | |
| - template:diffusion-lora | |
| widget: | |
| - output: | |
| url: images/ComfyUI_00876_.png | |
| text: '-' | |
| base_model: black-forest-labs/FLUX.2-klein-9B | |
| instance_prompt: null | |
| license: other | |
| license_name: flux-1-dev-non-commercial-license | |
| license_link: LICENSE | |
| # Expression Control | |
| <Gallery /> | |
| ## Model description | |
| Klein does not have LoRAs like the PixelSmile for QIE2511, so I decided to train a set myself! like the QIE2511 version, this collection allows for fine‑grained and linear control over facial expressions while maintaining high character consistency | |
| ### happy | |
|  | |
| ### sad | |
|  | |
| ### surprised | |
|  | |
| ### disgusted | |
|  | |
| ### angry | |
|  | |
| ### vigilant | |
|  | |
| ## Updating continuously …… | |
| # Continuously updating | |
| ## I'm an independent model and workflow developer. If you like my work and want to support independent development, please consider buying me a cup of coffee to keep this motivation going! Thank you very much. | |
| [support](https://www.patreon.com/posts/welcome-to-my-ai-151306281?utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=postshare_creator&utm_content=join_link) 🫡 May the AI-power be with you, see you soon !🫡 |