Venice SD35

• 🎨 Custom-configured Stable Diffusion 3.5 build, Venice's default image model.
• 🔒 Privacy-first: prompts and images stored locally, never on servers.
• 🔧 Runs a specialized ComfyUI workflow backend for optimized processing.
• 🆕 Launched within Venice Image Engine V2, March 2025.
• 📏 Accepts pixel-based width and height parameters, for example 1024×1024.
• ⚡ Pairs with a separate upscale-and-enhance system doubling or quadrupling resolution.
• 🌐 OpenAI-compatible API with optional watermark control.
• 🏢 Built on Stability AI's open Stable Diffusion 3.5 architecture.

Stability AI

Stability AI is a UK-based artificial intelligence company best known for creating Stable Diffusion, one of the most widely adopted text-to-image generation models in the AI ecosystem. The company has established itself as a leading force in open-weight…

Venice SD35 is Venice's self-hosted, privacy-preserving text-to-image model, built on Stability AI's open-source Stable Diffusion 3.5 architecture. Introduced as the default model in Venice Image Engine V2 in March 2025, it wraps the base SD 3.5 weights in a custom-configured engine powered by a ComfyUI workflow backend. Venice emphasizes that prompts and generated images remain in the user's local browser rather than on company servers, reflecting its privacy-first positioning.

According to Venice's own materials, the team runs a specialized pipeline configured for cleaner, sharper output than an off-the-shelf deployment. The Image Engine V2 release also pairs SD35 with a new upscaling system that doubles or quadruples resolution while preserving the original style and details, a recommended two-step workflow: generate first, then upscale and enhance.

Through the Venice API, the model is addressed by its identifier and accepts pixel-based sizing with width and height, alongside parameters such as step count, negative prompts, style presets, and an option to hide the watermark. The endpoints are OpenAI-compatible.

Venice SD35 sits within a broader Venice generative lineup that includes the adult-oriented image model Lustify SDXL and the audio-generation model Stable Audio 2.5, spanning images, music, and beyond under the same privacy-centric platform.