Text-to-Image
Diffusers
TensorBoard
Safetensors
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("peterholdsworth/output2", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Text-to-image finetuning - peterholdsworth/output2
This pipeline was finetuned from CompVis/stable-diffusion-v1-2 on the peterholdsworth/AND dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Please draw a mug with an ANDlogo logo']:
Pipeline usage
You can use the pipeline like so:
from diffusers import DiffusionPipeline
import torch
pipeline = DiffusionPipeline.from_pretrained("peterholdsworth/output2", torch_dtype=torch.float16)
prompt = "Please draw a mug with an ANDlogo logo"
image = pipeline(prompt).images[0]
image.save("my_image.png")
Training info
These are the key hyperparameters used during training:
- Epochs: 400
- Learning rate: 1e-05
- Batch size: 1
- Gradient accumulation steps: 4
- Image resolution: 512
- Mixed-precision: fp16
- Downloads last month
- 7
Model tree for peterholdsworth/output2
Base model
CompVis/stable-diffusion-v1-2