LLaDA-Image Models by InclusionAI

InclusionAIApache 2.0Open sourceOpen Source

2 models2026

Last refreshed 2026-09-08. Next refresh: weekly.

Details

ResearcherInclusionAI

LicenseApache 2.0OSI-approved

Commercial useCommercial use: permitted

Models2

Released2026

Capabilities

VisionAll models

MultimodalAll models

Links

Website HuggingFace

About

LLaDA-Image is InclusionAI's unified open image generation and editing family (Base and Turbo variants). Distinct from the LLaDA2.2 agentic diffusion language-model line.

Decision facts

Best fit: image generationimagevision and multimodal work
Capability starting point: LLaDA-Image with multimodal inputs
Lowest tracked input: Not tracked
Closest related family: K2 Horizon

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view

LLaDA-ImageCurrent

Use when the workload needs image generation, 6B parameters, and multimodal inputs.

2026-09image generation6B parametersmultimodal inputs

LLaDA-Image TurboCurrent

Use when the workload needs image generation, 6B parameters, and multimodal inputs.

2026-09image generation6B parametersmultimodal inputs

Current LLaDA-Image variants with use-when guidance and lifecycle status
Model	Use when	Released	Signals	Status
LLaDA-Image	Use when the workload needs image generation, 6B parameters, and multimodal inputs.	2026-09	image generation6B parametersmultimodal inputs	Current
LLaDA-Image Turbo	Use when the workload needs image generation, 6B parameters, and multimodal inputs.	2026-09	image generation6B parametersmultimodal inputs	Current