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.

Sem instalação: rode modelos de IA na nuvem

BitVector Prism é a forma mais fácil de começar: escolha um modelo, digite um prompt e gere em um app web limpo, sem configurar nada. O BitVector também está disponível no Discord e na web (SpyGlass).

Experimentar o BitVector

O que você precisa

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.

Como obter e instalar o 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.

Baixe apenas pelos links oficiais desta página. Instaladores de outros lugares podem estar desatualizados ou adulterados. O ModelTrends.ai não hospeda arquivos.

Sem instalação: rode modelos de IA na nuvem

O PirateDiffusion é exclusivo do Telegram e feito para profissionais: milhares de modelos, LoRAs e workflows por comandos de chat, com geração ilimitada a preço fixo.

Experimentar o PirateDiffusion

Como usar o 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.

Dicas e problemas comuns

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.

Modelos que você pode rodar no 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.

Modelos Stable Diffusion 1.5

Modelos Stable Diffusion XL 1.0

Modelos Flux

Sem instalação: rode modelos de IA na nuvem

Sem GPU, sem downloads, sem Python. Esses serviços rodam os mesmos modelos de código aberto em seus próprios servidores, então você começa a gerar pelo navegador, Discord ou Telegram em um minuto.

Experimentar o BitVector

Experimentar o PirateDiffusion

Links

Estes links levam aos sites dos próprios criadores. O ModelTrends.ai não é afiliado a eles e não hospeda software.

Outros apps locais

Como instalar o 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.