Laboratory
Entity that develops or publishes the model and maintains its technical and safety documentation.
VERIFIED ORGANISATION
Stability AI
Explore the documented models, published evaluations and primary sources associated with this organisation.
01 / MODELS
Verified catalogue
OPEN, SELF-HOSTABLE IMAGE MODEL
Stable Diffusion 3.5 Large
8B-parameter image base model for generation and editing, available via API and for self-deployment under a Stability license.
18 SEP 2026↗ TEXT AND AUDIO TO MUSICStable Audio 3.0
Commercial model for generating songs, instruments, and effects from text or audio, with inpainting and style transformation.
18 SEP 2026↗02 / EVALUATIONS
Published results
Figures are shown with the context reported by their source. A provider result is not an independent comparison and does not replace your own evaluation.
| Model | Benchmark | Result | Metric |
|---|---|---|---|
| Stable Diffusion 3.5 Large | Evaluación SD 3.5 Large | Main base model | Quality and prompt adherence |
| Stable Audio 3.0 | Evaluación Stable Audio 3 | Up to 6 min | Published duration and coherence |
03 / METHOD
How to read the directory
An organization, a product, and a model are not the same unit. Inferama separates them to avoid attributing capabilities or commercial terms to the wrong item.
Model
Identifiable version with limits, modalities, and behavior that may change between releases.
Access channel
API, application, associated cloud, or commercial plan; each channel may have different pricing, retention, and limits.
Source and date
Every claim must retain the official page consulted and the verification date.
ANALYSIS
Related analysis
Stable Audio 3 Under Evaluation: What the Metrics Measure and When Results Can Be Compared
A score alone does not describe the quality of an audio generator. This audit distinguishes the model, benchmark, and metric, and identifies the information that must be checked to interpret or reproduce Stable Audio 3 results.
30 Sep 2026 ↗
Stable Diffusion 3.5 Large put to the test: how to measure prompt following
A reproducible protocol for evaluating whether SD 3.5 Large follows specific visual instructions, comparing its results with Medium without confusing configuration differences, and reporting the limits of the evidence.
29 Sep 2026 ↗04 / SOURCES