DiffusionBee was the first drag-and-drop app that let Mac users run Stable Diffusion without any setup. It is a normal desktop application with a text to image screen, image to image, inpainting, outpainting, upscaling and a built-in model downloader. Everything runs locally and offline. Newer versions added Flux and SDXL and a Windows build.

DiffusionBee is for people who want the simplest possible start on a Mac and do not need advanced controls. If you later want LoRAs with fine control, ControlNet or video, Draw Things or ComfyUI go further.

Geen installatie nodig – draai AI-modellen in de cloud

BitVector Prism is de makkelijkste manier om te beginnen: kies een model, typ een prompt en genereer in een overzichtelijke web-app, zonder iets in te stellen. BitVector is ook beschikbaar op Discord en op het web (SpyGlass).

BitVector proberen

Wat je nodig hebt

macOS 13 or later; Apple Silicon (M1 or newer) with 16 GB RAM recommended for SDXL and Flux, 8 GB works for SD 1.5. Intel Macs run very slowly. The Windows build needs a 64-bit system and an NVIDIA GPU. Models are 2 to 12 GB each.

Zo krijg en installeer je DiffusionBee

Go to diffusionbee.com and download the version for your Mac (Apple Silicon or Intel) or for Windows.
Open the .dmg and drag DiffusionBee into Applications, then start it. The first start downloads the default model.
Open the Models screen to download more models (SDXL, Flux) from inside the app, or use Add New Model to import a .safetensors or .ckpt file from Civitai or Hugging Face.
Optional: import LoRAs in the same screen under the LoRA section; they become selectable in the generate options.

Download alleen via de officiële links op deze pagina. Installers van elders kunnen verouderd of gemanipuleerd zijn. ModelTrends.ai host geen bestanden.

Geen installatie nodig – draai AI-modellen in de cloud

PirateDiffusion is alleen op Telegram en gemaakt voor pro's: duizenden modellen, LoRA's en workflows via chatcommando's, met onbeperkt genereren voor een vaste prijs.

PirateDiffusion proberen

Zo gebruik je DiffusionBee

On the Generate screen, type your prompt, choose the model from the dropdown and press Generate.
Open Options to set the number of images, steps, guidance scale, size and seed, and to add a negative prompt.
Use Image to Image to transform a picture you drop in, with a strength slider; Inpainting and Outpainting let you paint a mask or extend the canvas.
Pick a LoRA in the options and add its trigger words from the model page to your prompt.
Finished images are in the History screen; click one to save it or reuse its settings.

Tips en veelvoorkomende problemen

Close other heavy apps while generating on 8 GB Macs; memory pressure slows generation a lot.
If an imported model does not load, make sure it is a standard SD 1.5, SDXL or Flux checkpoint and not a LoRA or a merged file in an unusual format.
Upscale results with the built-in upscaler instead of generating at large sizes; it is faster and uses less memory.
Check the site for updates; model support (Flux, SDXL) arrived through app updates.

Modellen die je in DiffusionBee kunt draaien

DiffusionBee runs Stable Diffusion 1.5, SDXL and Flux checkpoints and LoRAs from this catalog through its import feature.

Flux-modellen

Stable Diffusion XL 1.0-modellen

Stable Diffusion 1.5-modellen

Geen installatie nodig – draai AI-modellen in de cloud

Geen GPU, geen downloads, geen Python. Deze diensten draaien dezelfde opensourcemodellen op hun eigen servers, zodat je binnen een minuut kunt genereren vanuit een browser, Discord of Telegram.

BitVector proberen

PirateDiffusion proberen

Links

Deze links gaan naar de sites van de makers zelf. ModelTrends.ai is niet aan hen verbonden en host geen software.

Andere lokale apps

ComfyUI installeren

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.