Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
stable-diffusion

Stable Diffusion v1.4: ilustraciones de libros antiguos

Modelo completo: CompVis/stable-diffusion-v1-4 con la LoRA alvaroborre/sd-lora-oldbookillustrations fusionada en la UNet.

Entrenamiento: 600 imágenes de gigant/oldbookillustrations, 6 épocas, LoRA rango 6 / alpha 6, learning rate 0.0001, 512x512.

ejemplo

Uso

from diffusers import StableDiffusionPipeline
import torch
pipe = StableDiffusionPipeline.from_pretrained("alvaroborre/sd-oldbookillustrations", torch_dtype=torch.float16).to("cuda")
pipe("an image of a desert island").images[0]
Downloads last month
17
Safetensors
Model size
0.9B params
Tensor type
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for alvaroborre/sd-oldbookillustrations

Finetuned
(878)
this model

Dataset used to train alvaroborre/sd-oldbookillustrations