ruMeme Description model
Example
Use Diffusers >=0.8.0, do not support lower versions.
from diffusers import StableDiffusionPipeline
import torch
model_path = "foldl/sd-rumeme-desc"
pipe = StableDiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float16)
pipe.to("cuda")
image = pipe(prompt="кот").images[0]
image.save("cat".jpg)
Training
Training Procedure
Model was trained on 1 P100 GPU for 10k steps.
Base model - https://huggingface.co/OFA-Sys/small-stable-diffusion-v0
Training notebook here - https://www.kaggle.com/code/nukeee/meme-diffusion
Training Data
- https://huggingface.co/datasets/foldl/rumeme-desc
- Same dataset at Kaggle
- Downloads last month
- 8
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.