Text-to-Image
Diffusers
TensorBoard
English
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("YaYaB/sd-onepiece-diffusers4", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]sd-onepiece-diffusers4
Model description
This diffusion model is trained with the 🤗 Diffusers library
on the YaYaB/onepiece-blip-captions dataset.
Intended uses & limitations
How to use
# TODO: add an example code snippet for running this diffusion pipeline
Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
Training data
[TODO: describe the data used to train the model]
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- gradient_accumulation_steps: 4
- optimizer: AdamW with betas=(0.9, 0.999), weight_decay=0.01 and epsilon=1e-08
- lr_scheduler: constant
- lr_warmup_steps: 500
- ema_inv_gamma: None
- ema_inv_gamma: None
- ema_inv_gamma: None
- mixed_precision: fp16
Training results
- Downloads last month
- 9