Image generation

Stable Diffusion 3.5 Large

Name: Stable Diffusion 3.5 Large
Author: Stability AI

Stability AI's 8-billion-parameter open-weights flagship, a multimodal diffusion transformer aimed at roughly 1-megapixel output.

An image model by Stability AI · read 2026-08-14 · sourcing medium

Resolution: ~1 megapixel (Stability describes SD3.5 Large as ideal for professional use at 1 megapixel resolution)
Weights: Downloadable
API: Yes
Commercial use: Permitted subject to conditions

It ships alongside Large Turbo (fewer steps) and Medium (2.5B) variants and can be self-hosted or used through Stability's API and cloud partners. Free to use commercially below a $1M annual revenue threshold.

Commercial use — Permitted subject to conditions

EXACT LICENSE: 'Stability Community License' (also referred to as the Stability AI Community License Agreement).

Revenue threshold: free below $1,000,000 in annual revenue, chargeable above it.

Free only below a revenue threshold. Per Stability's license page and the model card: free for research, non-commercial and commercial use for individuals or organisations with less than USD $1M in total annual revenue

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Stability AI's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is mixed. Some fields came from pages we retrieved, others could not be confirmed and are left blank. Check the vendor's current documentation

What it takes in: text, image
What it makes: image
Maximum resolution: ~1 megapixel (Stability describes SD3.5 Large as ideal for professional use at 1 megapixel resolution)
Aspect ratios: not established
Controls: image-to-image, inpainting, outpainting, control-net-structure
Weights: Downloadable
API: Yes
Pricing: weights free to download; hosted API billed in credits (exact credit cost not verified — platform.stability.ai pricing page is JS-rendered and did not return content)
Released or updated: not established

Supported aspect ratios is not established here. That means no page we could retrieve stated it, not that the model lacks one.

Strengths

Genuinely permissive commercial terms below the $1M revenue line
Large ecosystem of fine-tunes, LoRAs and ControlNets
Self-hostable with three size/speed variants

Weaknesses

Roughly 1MP native output is low next to 2K/4K rivals
No successor announced; the open-weights lead has shifted to FLUX and others
Revenue threshold creates a compliance obligation as a studio scales

Best for

Self-hosted or heavily customised pipelines that need ControlNet-style structural control and permissive licensing at modest revenue.

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

Release date left null: the model card we fetched does not state the SD3.5 Large release date (it cites the 2024 SD3 paper). Third-party sources place it in October 2024.
Third-party sources report the hosted Stable Image Ultra API at $0.08/image; we could not verify any Stability credit or USD figure from a fetched Stability page.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

Conditioning and control: everything you hand the model besides noise names “outpainting”
Diffusion models: generation by denoising names “diffusion”
Camera control: a move without a camera names “control”
Open weights versus closed API: renting or owning the model names “weights”

MCP servers that front Stability AI

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

Audio Analyzer Audio and voice
Gives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis.
Audiolla Music
Self-hosted MCP server: audio stems, mastering, MIR analysis, DSP, MIDI, speech tools.
Civitai Image generation
Civitai MCP.
Cochlea Audio and voice
Render, analyze, and verify audio (WAV/FLAC/mp3/ogg) offline and deterministically via MCP tools.
Comfyui Image generation
MCP server + Claude Code plugin for ComfyUI: run workflows, generate images, manage models & VRAM.
Corent Image generation
Generate images and videos via the Corent API, auto model routing with provider fallback.

1 further server name Stability AI with lower confidence and are not listed, because a server naming a vendor may be using it for text rather than media.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Stable Image Ultra

Stability's highest-quality hosted text-to-image service on its developer platform, positioned above Stable Image Core and updated to run on the Stabl

Image generation

Adobe Firefly Image Model 5

Adobe's current Firefly image model, announced in public beta at Adobe MAX on 28 October 2025, generating at native 4 MP resolution without an upscale

Image generation

FLUX.1 Kontext [pro] / [max]

Instruction-driven image editing models from the FLUX.1 generation (2025), still exposed as live /flux-kontext-pro and /flux-kontext-max endpoints. Th

Image generation

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.