Bắt đầu nhanh

1. Install Telegram

Install Telegram on any of your devices. You can resume work across devices by being logged into all of them seamlessly.

2. Talk to @piratediffusion_bot and type /start

/start

That will talk you through setting up a cloud GPU to render the images. A data center compatible with PirateDiffusion is necessary, as your device isn't what creates the beautiful things: they're made on the cloud. That means no models, no installs and no AI anything on your device. We beam it down.

A compatible provider is Graydient.ai. Choose their Images plan for photos, Plus for short videos, or Max for longer videos and more images batched at a time. It's a flat-fee provider with no cost per creation, so we recommend it.

Type /debug to check that the bot is activated; if the reply says free-free, your GPU account is not connected yet.

3. Learn your first command: Skills

Type // to create or edit images and videos. You do not need to learn commands or pick a model first. Begin your request with two slashes and the bot picks the best Skill for it: the model, the workflow and the settings that fit your words. Copy this into the chat:

// a gray chubby cat napping in a sunny garden, photo

A confirmation message appears, then the pictures. The buttons under each result let you vote and upscale it.

Change the words and send it again. The more you describe, the closer the picture gets:

// a gray British shorthair cat asleep among peonies in a big garden, soft morning light, realistic photo

Videos work the same way

Ask for motion and the bot picks a video Skill:

// a short video of waves rolling onto a black sand beach at sunset

Edit a photo

Send a photo into the chat first, then reply to it with your request. Putting the word edit in it helps the bot pick an editing Skill:

// edit, make her hair blonde

Pick a Skill yourself

Every Skill also has a name you can run directly, for example /anime-illustrious a warrior standing in the rain. /skill /list shows the Skills available to you, /skill /show:name describes one, and /skill /tune lets you mute the ones you never want picked for you.

When you want full control

The /render and /workflow commands name the exact model, size, steps and seed yourself. That is what the How to prompt lessons and the commands list are for. The original SDXL beginner lesson, with its /render cat examples and bracket weights, is kept as a 2024 guide.