Stable-Diffusion-Colab

The goal of this repository is to provide a Colab notebook to run the text-to-image "Stable Diffusion" model [1].

Usage

• Run stable_diffusion.ipynb.

Schedulers

A scheduler [2] can be chosen among:

• PNDM, which is the default scheduler in 🤗's D🧨iffusers for Stable Diffusion at 512 resolution,
• DDIM, which is the default scheduler in 🤗 for Stable Diffusion at 768 resolution,
• K-LMS, which is the scheduler suggested by DreamStudio.
• Euler, which is the scheduler used in 🤗's example for Stable Diffusion 2.
• DPM, which is the scheduler used in 🤗's example for Stable Diffusion 2.1.

Parameters

Typically, parameters are set with the following ranges in mind:

• num_images (default: 4), between 1 and 4,
• guidance_scale (default: 9), between 0 and 20,
• num_inference_steps (default: 25), between 10 and 150.

Results

_{Different results obtained with the text prompt: "a photo of an astronaut riding a horse on Mars".}

---

_{Different results obtained with the text prompt: "a photo of an astronaut riding a horse on Mars" using Dreamlike Photoreal 2.0.}

---

_{Different results obtained with the text prompt: "a photo of Pikachu fine dining with a view to the Eiffel Tower".}

---

_{Different results obtained with the text prompt: "a photo of Pikachu fine dining with a view to the Eiffel Tower" using Dreamlike Photoreal 2.0.}

References

[1] Rombach, Robin, et al. High-resolution image synthesis with latent diffusion models. CVPR 2022. (models & demo)

[2] Karras, Tero, et al. Elucidating the Design Space of Diffusion-Based Generative Models. NeurIPS 2022. (code)