Instructions to use Basunat/Cinematic-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Basunat/Cinematic-Diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Basunat/Cinematic-Diffusion", 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
Update README.md
#1
by Basunat - opened
This model is called "Cinematic Diffusion". It has been trained on Stable Diffusion 2.1 to get cinematographic images. To make it works you have to write at the beginning of the prompt the keyword "syberart".
The model works very well in square format, but given its cinematic nature it gives better results in 16:9 format.
Use base prompts with small modifications to achieve 'screengrabs' of movies of many genres: historical, sci-fi, fantasy, spy, horror movies, western films, mystery movies, comedy, superhero movies, anime, etc. But it also works well for realistic portraits, landscapes, etc. It has a general use as well.









