Easy Diffusion (formerly cmdr2 UI) is a free program that installs Stable Diffusion with a single download and gives you a clean browser interface: prompt, a few sliders, a queue, image modifiers you can click, live preview and face fixing. It has none of the complexity of node graphs and does not require Python or Git to be installed first.

A good first app for beginners on any platform, and for low-end machines, since it can run on CPU and on 4 GB cards. If you grow out of it, Forge or ComfyUI pick up where it stops.

Bez instalace - spouštějte AI modely v cloudu

BitVector Prism je nejsnazší způsob, jak začít: vyberte model, napište prompt a generujte v přehledné webové aplikaci, bez jakéhokoli nastavování. BitVector je k dispozici také na Discordu a na webu (SpyGlass).

Vyzkoušet BitVector

Co potřebujete

Windows 10 or 11, Linux or macOS. NVIDIA GPU with 4 GB VRAM or more recommended; AMD on Linux; Apple Silicon supported; it also runs (slowly) on CPU. 8 GB system RAM and about 25 GB of free disk space including the default model.

Jak získat a nainstalovat Easy Diffusion

Download the installer for your system from easydiffusion.github.io.
Windows: run the downloaded file and let it extract to a folder without spaces (for example C:\EasyDiffusion). Mac and Linux: unzip and run the start script.
Start Easy Diffusion with Start Stable Diffusion UI.cmd (Windows) or start.sh. The first start downloads the required files and a default model and opens http://localhost:9000.
Put extra checkpoints in models/stable-diffusion, LoRAs in models/lora, VAEs in models/vae and embeddings in models/embeddings; they appear in the dropdowns after a refresh.

Stahujte pouze z oficiálních odkazů na této stránce. Instalátory nalezené jinde mohou být zastaralé nebo upravené. ModelTrends.ai nehostuje žádné soubory.

Bez instalace - spouštějte AI modely v cloudu

PirateDiffusion je pouze na Telegramu a je stavěný pro profesionály: tisíce modelů, LoRA a workflow ovládaných chatovými příkazy, s neomezeným generováním za pevnou cenu.

Vyzkoušet PirateDiffusion

Jak používat Easy Diffusion

Type a prompt, optionally a negative prompt, and press Make Image. The image renders with a live preview in the queue.
Open Image Settings to pick the model, the size, the steps, the guidance scale, the sampler and the number of images.
Click Image Modifiers to add style words (artists, mediums, moods) to your prompt by clicking tiles.
Pick a LoRA in the Image Settings and add its trigger words from the model page; use the strength slider to tune its effect.
Drop an image onto the initial image box for image to image or inpainting; enable Fix Faces (GFPGAN) and Upscale (Real-ESRGAN) under the image.

Tipy a časté problémy

Turn on Low VRAM mode in the settings on 4 GB cards; it is slower but avoids out of memory errors.
Use the beta channel in the settings to try new features, or stay on main for stability.
Prompts with | create several variations in one go; each gets its own image.
All settings are stored per browser; use the Save Settings option so they persist.

Modely, které lze spustit v Easy Diffusion

Easy Diffusion runs Stable Diffusion 1.5 and SDXL checkpoints, LoRAs and embeddings from this catalog; newer versions also load Flux models. It is not suited for video models.

Modely Stable Diffusion 1.5

Modely Stable Diffusion XL 1.0

Modely Flux

Bez instalace - spouštějte AI modely v cloudu

Žádná GPU, žádné stahování, žádný Python. Tyto služby spouštějí stejné open source modely na vlastních serverech, takže můžete začít generovat z prohlížeče, Discordu nebo Telegramu během minuty.

Vyzkoušet BitVector

Vyzkoušet PirateDiffusion

Odkazy

Tyto odkazy vedou na weby samotných tvůrců. ModelTrends.ai s nimi není spojen a nehostuje žádný software.

Další lokální aplikace

Jak nainstalovat 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.