This is the fine-tuned Stable Diffusion model trained on movie stills from Sony's Into the Spider-Verse.
Use the tokens spiderverse style in your prompts for the effect.
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.
1#!pip install diffusers transformers scipy torch
2from diffusers import StableDiffusionPipeline
3import torch
4
5model_id = "nitrosocke/spider-verse-diffusion"
6pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
7pipe = pipe.to("cuda")
8
9prompt = "a magical princess with golden hair, spiderverse style"
10image = pipe(prompt).images[0]
11
12image.save("./magical_princess.png")
This model was trained using the diffusers based dreambooth training and prior-preservation loss in 3.000 steps.
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
The CreativeML OpenRAIL License specifies:
