Text-to-Image
Diffusers
Safetensors
English
StableDiffusionPipeline
stable-diffusion
image-to-image
nitrosocke
Instructions to use Yntec/GhibliDiffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Yntec/GhibliDiffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Yntec/GhibliDiffusion", 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
metadata
language:
- en
license: creativeml-openrail-m
tags:
- stable-diffusion
- text-to-image
- image-to-image
- diffusers
- nitrosocke
Ghibli Diffusion
768x768 safetensors version of this model, also includes a version with the kl-f8-anime2 baked in, used by the serverless API. Samples and prompts (all use seed 9119):
ghibli style princess zelda portrait
ghibli style VW beetle
ghibli style highquality, masterpiece, 1girl, Chi-Chi, close up, arms up, pink helmet, black hair, black eyes, blush, white teeth, bikini armor, aqua cape, pink gloves, pink boots, cleavage. cave, rock, mountain. blue collar, CHIBI.
ghibli style ice field white mountains ((northern lights)) starry sky low horizon
For the original CKPT version check:
https://huggingface.co/nitrosocke/Ghibli-Diffusion



