Instructions to use p1atdev/Realgar-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use p1atdev/Realgar-v2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("p1atdev/Realgar-v2", 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 Settings
- Draw Things
- DiffusionBee
[Discussion] Replacing camera with super personalized models
Hello platdev,
This is Eric Maeng, Co-founder at Studio Peekaboo
First of all, I appreciate your contribution toward SD scripts. We were so much inspired by kohya scripts.
At Studio peekaboo, we make AI-generated studio headshots to 600 ~ 1000 Korean female users a day. Customers love the photo-realistic quality. Yet making headshots is not our end goal.
We aim to replace the camera. We envision a future where people upload pictures of their lives on instagram all generated or modified with super personalized models.
Our recent challenge lies in super resemblance and avoiding deformed hands/eyes. I'd love to discuss our challenges with you and let you hear our vision toward super personalized models. Also I want to hear your view on training model and pre/after processing for our purpose
Let me know if you are interested.
You can check our web service here : https://www.peekaboo.style/#review
Appended are pictures from one of our users and images generated based on that.




