import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Ryzan/fantasy-diffusion-v1", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]fantasy-diffusion-v1 diffusion ML model by Ryzan (Ryan Han)
This is currently a base model
trained by me with DreamBooth
This model is trained on 400 images of semi-realistic fantasy art
(mostly female so expect results to be mostly female too)
This model does not use any finetuning techniques such as face restoration or in-painting as of yet
To get the fantasy style, write 'fantastyle' before your prompt (ex: 'fantastyle girl')
In addition, adding the any of the following words makes it higher quality: highly detailed, intricate, 4k, 8k, sharp focus, detailed hair, detailed
Sample pictures of this concept:
| Prompt: fantastyle foxgirl | Prompt: fantastyle foxgirl |
|---|---|
 |
.jpg) |
| Prompt: fantastyle knight | Prompt: fantastyle knight |
|---|---|
 |
.jpg) |
| Prompt: fantastyle mage | Prompt: fantastyle mage |
|---|---|
 |
.jpg) |
- Downloads last month
- 51