Waltz With Bashir Diffusion

🚀 Stable Diffusion v1.5 fine tuned on Waltz with Bashir screencaps

This project is a fine - tuned Stable Diffusion v1.5 model based on the screencaps of "Waltz with Bashir". It offers unique text - to - image generation capabilities.

🚀 Quick Start

To use this model, you need to use the specific prompt: 'wltzwthbshr'. You can check out Waltz with Bashir on IMDB.

💻 Usage Examples

Basic Usage

The following settings were used for the output samples: "wltzwthbshr SUBJECT", euler a, 35 steps, cfg 7, 1024x1024, high res fix on, sd - vae - ft - mse - original (AUTOMATIC1111 webui).

Here are some output samples:

Advanced Usage

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

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

from diffusers import StableDiffusionPipeline
import torch
model_id = "mikesmodels/Waltz_with_Bashir_Diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "wltzwthbshr dwayne johnson"
image = pipe(prompt).images[0]
image.save("./dwayne_johnson.png")

📄 License

This model is under the creativeml - openrail - m license.