ANTI-AI ARCHIVE
ART-HISTORY NODE / 264 · 2024-11-26

SD3.5 ControlNets

SD3.5 ControlNets

Stability AI

Introduction

Canny, Depth and Blur controls make the new Stable family usable in precise production workflows.

SOURCE IMAGE#264
SD3.5 ControlNets: illustration from the cited release page. Lettering retains its original language. This is a source illustration, not a sample generated by this archive.View full image ↗

SD3.5 ControlNets: illustration from the cited release page. Lettering retains its original language. This is a source illustration, not a sample generated by this archive.

Stability AI · source publication · Image rights remain with their respective holders; no open licence is asserted

Source · SD3.5 ControlNets ↗

RESEARCH ACCOUNT

External structure can constrain how a model changes an image.

ANTI-AI ARCHIVE · Revised 2026-10-02

Release and use

The November 2024 SD3.5 ControlNets release includes Blur, Canny and Depth. Edge and depth inputs provide structural conditions, while blurred input supports tasks such as detail reconstruction. These supplement a base model rather than replicating generation from text alone.

Section sources: SD3.5 ControlNets

Change in creative practice

Control concerns relationships to preserve: outlines, spatial placement or source structure. A reference is thus computational material, not merely an inspirational label. Recording these constraints explains how an output can be newly generated while continuing the arrangement of an existing image.

Section sources: SD3.5 ControlNets

Sources for this account

SD3.5 ControlNets ↗

Official release scope and demonstration descriptions read; vendor performance claims are not treated as independent test results.

This account expands the archive within the cited scope. Historical interpretation is not presented as the original author’s statement or as a proven causal influence. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.

Continue with a comparative question

Adding Conditional Control to Text-to-Image Diffusion Models ↗

Compare the methods, forms of control or presentation contexts of this entry and Adding Conditional Control to Text-to-Image Diffusion Models.

FLUX.1 Tools ↗

Compare the methods, forms of control or presentation contexts of this entry and FLUX.1 Tools.

Dates & version record

Date displayed for this node: 2024-11-26 · Historical date recorded for the source: 2024-11-26

These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.

Original sources & further reading

These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.

01
SD3.5 ControlNets ↗

SD3.5 ControlNets

https://stability.ai/news-updates/sd3-5-large-controlnets

Current cited URL

This is the archive’s bilingual research abstract. The external link is an original source, not a claim that the publisher offers full text in both languages.

Provenance, translation & verification

Timeline entry #264 · Open model

Research materials & supplement references · 1

GenAI Visual Release Chronology Research Master · p. 25 · R135
Date as recorded: 2024-11-26
SD3.5 ControlNets ↗
SD3.5 ControlNets

Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.

The master’s research claims and dates await independent verification.

Cite this node

ANTI-AI ARCHIVE. SD3.5 ControlNets. Art-history node #264. https://salondesrefuses.cn/en/art-history/189

For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.

Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.