Draw Things vs Stable Diffusion WebUI Forge

Draw Things is an AI image-generation app for creating images from text prompts, with models that can be downloaded and run locally, including offline. Its tools include image editing, reference images, an infinite canvas, image styling, apparel prototyping, and on-device LoRA training. It can also make video clips from images. The Free Edition includes local compute, model downloads, the canvas, and local LoRA training. Community accounts can use free cloud compute. Draw Things+ costs $8.99 a month and adds higher cloud compute limits, use of personal LoRAs with Cloud Compute, on-demand compute boosts, and Privacy Pass. Enterprise plans cover organizational deployment, on-premise inference hosting, and local or cloud integration into customer apps. Most creations and data can be stored locally under user control. Cloud Compute requires sign-in, and uploaded LoRAs are held on third-party cloud servers; encryption in transit and at rest is stated. The privacy policy says the app uses no third-party analytics or advertising frameworks for tracking. The maker is Draw Things, Inc.

Stable Diffusion WebUI Forge is a free, open-source platform built on Stable Diffusion WebUI for image generation and editing. It supports text-to-image creation, reference images, and image editing, with PNG, JPG, JPEG, WebP, AVIF, and GIF listed as output formats. The project aims to ease development, manage resources, speed inference, and explore experimental features. Its interface is based on Gradio, and the README offers a one-click installation package that includes Git and Python. Windows launch scripts, shell scripts, a macOS environment script, and source installation instructions are listed. Forge includes GPU memory management and components such as LoRAs, ControlNets, IP-Adapters, Instant-IDs, reference-only methods, and extensions. Several Flux BitsandBytes and GGUF variants are natively supported, with GPU weight and swap controls; some variants support LoRA. The README lists txt2img and img2img API endpoints as normal, while improved Flux support is pending. The project is described as under construction, so its documentation, interface, and functionality may change. Its license is AGPL-3.0.