Apps in this category may contain mild or occasional cartoon, fantasy or real-life violence, as well as occasional or mild adult, sexually suggestive or horrifying content and may not be suitable for children under 9 years of age.

12+

Apps in this category may contain occasional mild indecent language, frequent or intense cartoon or real-life violence, minor or occasional adult or sexually suggestive material, and simulated gambling, and may be for children under 12 years of age.

17+

You must be at least 17 years old to access this App.

Apps in this category may contain frequent and intense offensive language; Frequent and intense cartoon, fantasy or realistic violence: frequent and intense adult, scary and sexually suggestive subjects: as well as sexual content, nudity, tobacco, alcohol and drugs, may not be suitable for children under 17 years of age.

AI Photo 螢幕截圖

iPad

iPhone

About AI Photo

Turn text into images! AI Photo is a user-friendly text-to-image generator app that creates photos and artworks, all offline, based on your image description.

Features
• AI-powered Text-to-Image generator
• Supercharged by Stable Diffusion
• Privacy by Design: Computes offline, directly on your Mac, iPhone or iPad
• Fast: Optimised for Apple silicon chips (M1, M2)
• Collections: Organise and manage your artworks
• Favourites: Your best creations always at hand
• Search: Lightning fast, surprisingly smart
• Pros in Mind: Change Steps, Seeds, Guidance Scales
• Custom Models: On the Mac, you can add custom CoreML models.
• Export & Share
• Looks brilliant in dark and light

System Requirements (Mac)
• Apple M1 or M2 chip (Apple silicon)
• 16 GB of RAM, the more the better
• Intel-based Macs are currently not supported

System Requirements (iPhone, iPad)
• Current generation device (2021 or newer)
• 8 GB of RAM, the more the better

Benchmarks
• AI Photo runs offline, directly on your hardware, and therefore depends heavily on your devices resources.
• iPhone 14 (2022): 1 image @ 20 steps takes about 4 minutes
• MacBook Pro, M1 Pro (2021): 1 image @ 20 steps takes about 30 seconds

Model: Use, Misuse and Limitations
• AI Photo ships with a built-in Stable Diffusion model.
• This model is intended for research purposes only.
• The model was trained on the large-scale dataset LAION-5B. It has limitations and biases. For example, it only understands English prompts.
• Additional safety mechanisms were implemented which limits possible outcomes.
• Do not misuse the model to create harmful content.
• By using this app you confirm that you have read and accepted our Terms of Use as well as the Stable Diffusion License (linked below).

⁂

Stable Diffusion Model License: https://huggingface.co/spaces/CompVis/stable-diffusion-license
Stable Diffusion LAION-5B Dataset: https://laion.ai/blog/laion-5b/

Terms of Use: https://ixeau.com/terms
Privacy Policy: https://ixeau.com/legal#privacy