Tardisfusion

作者 Guizmus · 下载 30 · 点赞 12 · 更新 2023-11-01

stable-diffusion text-to-image image-to-image

TARDISfusion

Tardisfusion 预览 1
This is a Dreamboothed Stable Diffusion model trained on 3 Style concepts.
The total dataset is made of 209 pictures, and the training has been done on runawayml 1.5 with 2500 steps and the new VAE. The following tokens will add their corresponding concept :

CKPT download link

🧨 Diffusers

This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion.

You can also export the model to ONNX, MPS and/or FLAX/JAX.

from diffusers import StableDiffusionPipeline
import torch

model_id = "Guizmus/Tardisfusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "a bedroom, Classic Tardis style"
image = pipe(prompt).images[0]

image.save("./TARDIS Style.png")