How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("wojols/FishVision", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

Model info:

https://civitai.com/models/111636/fishvision
Sample images

Training

Steps: 1,000
Dataset: 103 images

Usage Tips

Trigger Words: FISH, FISHES
Clip skip: 2
Sampler: DPM++ 2M SDE
Downloads last month
6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support