import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Aktraiser/text_image", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Fine-Tuned Text-to-Image Model
This model is a fine-tuned version based on Wan2.1-T2V-14B.
Note on Model Weights
Due to disk space limitations, the full model weights may not be included in this repository. The model was fine-tuned on a custom dataset for 10 steps with a learning rate of 0.0001.
Loading
from diffusers import DiffusionPipeline
model = DiffusionPipeline.from_pretrained("your-username/text-image")
Parameters
- Steps: 10
- Learning rate: 0.0001
- Optimizer: adamw_8bit
- Downloads last month
- -