Draw Things is a free native app for Apple devices that runs image and video models directly on Apple Silicon and even on recent iPhones and iPads. It downloads models from its own library (converted to run efficiently on Apple hardware), supports LoRAs, ControlNet, inpainting, outpainting and video, and works fully offline. The core is open source as the community edition; the App Store version is free.

If you have a Mac, iPhone or iPad and want local generation without Python, Draw Things is the easiest and fastest path. It is also unique in running serious models on a phone. Windows and Linux users need another app.

Tiada pemasangan diperlukan - jalankan model AI di awan

BitVector Prism ialah cara paling mudah untuk bermula: pilih model, taip prompt dan jana dalam aplikasi web yang bersih, tanpa apa-apa untuk dikonfigurasi. BitVector juga tersedia di Discord dan di web (SpyGlass).

Cuba BitVector

Apa yang anda perlukan

macOS 13 or later on Apple Silicon (M1 or newer; Intel Macs are limited), or iPhone and iPad with an A14 chip or newer and iOS 16 or later. 8 GB of memory runs SD 1.5 and SDXL; 16 GB or more is recommended for Flux and video. Model files range from 2 GB to over 20 GB, so free up storage.

Cara mendapatkan dan memasang Draw Things

Open the App Store on your Mac, iPhone or iPad and install Draw Things: AI Generation. It is free.
Open the app and tap the model selector at the top; pick a model from the built-in list (for example SDXL, Flux schnell or Wan) and download it inside the app.
To import your own .safetensors files on a Mac, choose Import Model in the model menu and point it at the file; Draw Things converts it.
Optional: install the community edition from GitHub if you want to build from source, or use the gRPC server to run the engine on a Mac and generate from an iPhone.

Muat turun hanya daripada pautan rasmi di halaman ini. Pemasang yang ditemui di tempat lain mungkin lapuk atau telah diubah suai. ModelTrends.ai tidak menghoskan sebarang fail.

Tiada pemasangan diperlukan - jalankan model AI di awan

PirateDiffusion hanya di Telegram dan dibina untuk profesional: beribu-ribu model, LoRA dan aliran kerja yang dipacu oleh arahan sembang, dengan penjanaan tanpa had pada pelan harga tetap.

Cuba PirateDiffusion

Cara menggunakan Draw Things

Type your prompt in the text box at the bottom and tap Generate. The image appears on the canvas.
Open the settings panel (the sliders icon) to set the size, steps, guidance scale, sampler and seed. The app suggests sensible defaults per model.
Add a LoRA from the LoRA section in the settings; download it from the list or import a file, set its weight and add the trigger words from the model page.
Paint over part of the canvas with the eraser or brush and generate again to inpaint; move the frame outside the image to outpaint.
Use ControlNet (pose, depth, canny, scribble) from the Control section to guide the composition from a reference image.
Pick a video model (Wan, Hunyuan) and set the number of frames in the settings to generate short clips; export them from the history panel.

Petua dan masalah biasa

On an iPhone, start with SD 1.5 or Flux schnell models at smaller sizes; large models can be slow or run out of memory.
Turn on the Metal FlashAttention and the 8-bit options in the settings to save memory on 8 and 16 GB machines.
The history panel keeps every generation with its full settings; long press to reuse them.
Draw Things has an active Discord and documentation site; model conversion questions are answered there.

Model yang boleh dijalankan dalam Draw Things

Draw Things runs Stable Diffusion 1.5, SDXL, Flux, Qwen Image, Hunyuan and Wan models and their LoRAs from this catalog; the in-app library covers the popular ones and you can import the rest on a Mac.

Model Flux

Model Stable Diffusion XL 1.0

Model Stable Diffusion 1.5

Model Wan

Model Qwen

Model Hunyuan

Tiada pemasangan diperlukan - jalankan model AI di awan

Tiada GPU, tiada muat turun, tiada Python. Perkhidmatan ini menjalankan model sumber terbuka yang sama pada pelayan mereka sendiri, jadi anda boleh mula menjana dari pelayar, Discord atau Telegram dalam seminit.

Cuba BitVector

Cuba PirateDiffusion

Pautan

Pautan ini menuju ke laman pembuat sendiri. ModelTrends.ai tidak bergabung dengan mereka dan tidak menghoskan sebarang perisian.

Aplikasi tempatan lain

Cara memasang ComfyUI

The node-based powerhouse for Stable Diffusion, Flux, Wan video and almost every new open source model. Free, open source, for Windows, Mac and Linux.