Sensitive Content Filter

Sogni Web and Sogni Studio for Mac have separate Sensitive Content Filter controls. In Sogni Web, the setting controls access to optional models for mature themes. In Studio for Mac, an on-device classifier screens generated images before they're shown in the gallery.

#Sogni Web

To turn off the filter in Sogni Web:

1. Open app.sogni.ai and sign in.
2. Select your username in the top-right corner of the screen.
3. Under Content preferences, switch off Sensitive Content Filter.
4. Confirm that you are 18 or older when prompted.

Mature-theme generation is strictly opt-in. You can return to the same menu and switch the filter on again at any time.

The switch is saved in the browser you set it in. It does not follow you to another browser or device, Sogni Chat keeps its own separate switch, and neither one applies to the API — see API and SDK below.

#What switching it off reveals

Turning the filter off surfaces the mature-theme Supernet models and LoRAs, and also the vendor video models tuned for mature themes. Wan 3 Uncensored — model ID wan3.0-spicy-video — then appears under Wan 3 version inside the Wan 3 workspace. Switch the filter back on and any workspace still set to Uncensored falls back to standard Wan 3.

#Sogni Studio for Mac

In the right-hand Manual Controls sidebar, expand the Advanced section. The Sensitive Content Filter toggle is there alongside Sampler, Processing, and Preview Count.

• Sensitive Content Filter ON/OFF — turn the classifier on or off.

In Video Create mode the same toggle lives in the Render Settings panel.

#How the Studio filter works

The filter is a small Core ML model that runs locally on your Mac via the Vision framework — every generated image is classified after it lands and before the gallery thumbnail renders. Nothing about your generations leaves the device for filtering purposes; the classifier weights live inside the app bundle.

When an image is flagged:

• Its gallery thumbnail is blurred.
• A tap / click reveals the unblurred version with a one-time confirmation.
• The image is tagged in metadata so you can filter the gallery by NSFW status later.

#API and SDK

On the API the filter is a per-request parameter, safe_content_filter, and it defaults to true. No switch in any app changes that, and there is no account-wide setting to turn off — send the parameter on each call:

• Chat Completions — top-level safe_content_filter on POST /v1/chat/completions.
• Creative Agent Workflows — top-level safe_content_filter on POST /v1/creative-agent/workflows, and on POST /:id/resume to release a run that paused on safety_review_required.
• Creative Agent CLI — --no-filter.

Turning it off needs an eligible account — an active Sogni subscription, Premium Spark, or paying with SOGNI. Sogni re-checks eligibility on every render, so an ineligible account is refused at generation time even when the parameter is set.

#When to use it

• Public demos / streaming. Keep it on so an unexpected result doesn't make it onto a shared screen.
• Shared family Macs. On at startup is the right setting.
• Concept art / private work. Off is fine when you're the only one looking at the gallery.

The filter is a screen for content visibility, not a hard generation block — the underlying model still produced the image, and clicking through always works. If you need a hard block at generation time, choose models tuned for safe content and keep prompts on the safe side.

#See also