import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("uhuya/FantasticVibes", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]FantasticVibes (SDXL)
FantasticVibes
Model Details
- Developed by: uhuya
- Model Type: Diffusion-based text-to-image generative model
- Base Model: SDXL 1.0
- Language(s): English
- License: CreativeML Open RAIL++-M
Versions & Recommended Settings
1. Normal Version
Best for sharp focus, realistic skin textures, and cinematic lighting.
- Sampler:
DPM++ SDEorDPM++ 2M SDE - Steps: 15 - 70
- CFG Scale: 5 - 7
2. Anima Version
Optimized for speed and a smooth "2.5D" artistic look.
- Sampler:
EulerorLCM - Steps: 10 - 30
- CFG Scale: 2 - 5
3. Anime Style
The definitive modern anime aesthetic with clean lineart and vibrant colors.
- Sampler:
Euler``DPM++ SDEorDPM++ 2M SDE - Steps: 15 - 70
- CFG Scale: 3 - 7
Limitations and Bias
This model is intended for artistic purposes. Users are encouraged to use the model responsibly and adhere to the license terms. It may reflect biases present in the training data.
- Downloads last month
- 14
Model tree for uhuya/FantasticVibes
Base model
stabilityai/stable-diffusion-xl-base-1.0