Downloads · 30 days
3
25% of all-time downloads
middles_kanjiv1
middles/middles_kanjiv1
middles_kanjiv1 is a text-to-image model from middles. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
This pipeline was finetuned from CompVis/stable-diffusion-v1-4 on the middles/kanjiv1 dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['This is a Japanese Kanj…
All-time downloads
12
Public
Parameters
860M
29.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.1 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Jan 27, 2024
- Updated
- Jan 28, 2024
- SHA
- 14bff28e
Base models
Datasets
Model card
From the Hugging Face model README
Text-to-image finetuning - middles/middles_kanjiv1
This pipeline was finetuned from CompVis/stable-diffusion-v1-4 on the middles/kanjiv1 dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['This is a Japanese Kanji character. Its meaning(s) is/are: climate change']:
Pipeline usage
You can use the pipeline like so:
from diffusers import DiffusionPipeline
import torch
pipeline = DiffusionPipeline.from_pretrained("middles/middles_kanjiv1", torch_dtype=torch.float16)
prompt = "This is a Japanese Kanji character. Its meaning(s) is/are: climate change"
image = pipeline(prompt).images[0]
image.save("my_image.png")
Training info
These are the key hyperparameters used during training:
- Epochs: 10
- Learning rate: 1e-05
- Batch size: 1
- Gradient accumulation steps: 4
- Image resolution: 512
- Mixed-precision: fp16
More information on all the CLI arguments and the environment are available on your wandb run page.
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Created
- Jan 27, 2024
- Updated
- Jan 28, 2024