Instructions to use SG161222/Paragon_V1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SG161222/Paragon_V1.0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("SG161222/Paragon_V1.0", 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
Please read this!
This model is in the testing phase. The necessary VAE is already baked into the model.
The recommended negative prompt:
(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4), (deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation, easynegative, bad-hands-5
Recommended parameters for generation:
Sampling method: Euler A
CFG Scale: 5-12
Clip Skip: 2
Hires.Fix Parameters:
Upscaler: Latent or other
Hires Steps: 0 or other
Denoising Strength: 0.35 - 0.7
Upscaled by: 1.1 - 2.0
Examples:
- Downloads last month
- 155