muhammad-taqi512/VINZING-TINY

DEVELOPER

DEVELOPER NAME : MUHAMMAD TAQI

Pipeline usage

You can use the pipeline like so:

from diffusers import DiffusionPipeline
import torch

pipeline = DiffusionPipeline.from_pretrained("muhammad-taqi512/VINZING-TINY", torch_dtype=torch.float16)
prompt = "Portrait of a pretty girl"
image = pipeline(prompt).images[0]
image.save("my_image.png")

Training info

These are the key hyperparameters used during training:

• Steps: 125000
• Learning rate: 1e-4
• Batch size: 32
• Gradient accumulation steps: 4
• Image resolution: 512
• Mixed-precision: fp16

Here is the code for benchmarking the speeds.