Microsoft AI's real-time speech-to-text model for voice agents, transcribing 60 languages with continuous language detection
TrustList summary
At 8.1 billion parameters, Stable Diffusion 3.5 Large is the base image model that Stability AI calls the most powerful in the Stable Diffusion family, and it suits professional work at 1 megapixel resolution.
Where Large sits among the 3.5 variants
Stability AI announced Stable Diffusion 3.5 as an open release with several variants. Large Turbo is a distilled version of Large that produces high-quality images, with strong prompt adherence, in only four steps, which makes it considerably faster. Medium, added to the announcement later, has 2.5 billion parameters, an improved MMDiT-X architecture, and output from 0.25 to 2 megapixels. The company says Medium needs only 9.9 GB of VRAM, excluding text encoders, so it fits most consumer GPUs. The release follows Stable Diffusion 3 Medium, which Stability says fell short of its own and the community's expectations, and it chose to build a better version rather than patch it quickly.
Built to be fine-tuned
Customisability was the priority. Query-Key Normalization was added to the transformer blocks to steady training and make later fine-tuning simpler. The announcement admits the trade-offs: the same prompt can give more varied results from one seed to the next, loosely worded prompts may produce more uncertain output, and the aesthetic level can vary. The company presents this as deliberate, because it keeps a broader knowledge base and a wider range of styles in the base models.
Licence and where to get it
The models are free for commercial and non-commercial use under the Stability AI Community License. Weights can be downloaded from Hugging Face and the inference code is on GitHub. A related announcement says Large is also available in Amazon SageMaker JumpStart.
Summary written by TrustList from the business's own published information, Nov 2026.
Benchmarks & AI stats
| Benchmark | Official | Community avg |
|---|---|---|
| No benchmark scores yet. Be the first to add one. | ||
“Official” values are editor-approved and feed the ranking. “Community avg” is the mean of member submissions (shown for transparency; it never affects the ranking until an editor approves a value).
Sign in to add a benchmark score for this model.
Stable Diffusion 3.5 Large launches
Request a demo or quote from Stable Diffusion 3.5 Large
Reviews
Write the first review of Stable Diffusion 3.5 Large
Used it? Your experience helps other buyers decide.
Write a reviewQuestions & answers
No questions yet. Be the first to ask about Stable Diffusion 3.5 Large.
Stable Diffusion 3.5 Large alternatives
Similar listings buyers compare against this one.
JetBrains' open 12B mixture-of-experts coding model with 2.5B parameters active per token under Apache 2.0
Aleph Alpha's open-weight English-German mixture-of-experts model for self-hosting, released under Apache 2.0 in October 2026
Open-weight translation model from Bilibili's Index team, covering 150 languages and following glossary and style instructions
Perplexity's open-weight decision model that picks among given options for routing and checks in AI systems
Cantina Security's first open-weight security model, a post-trained GLM-5.3-Flash for vulnerability research and exploit checks
Anthropic's smallest and fastest Claude 5.5 model, available on its own API and three cloud platforms
Liquid AI's open-weight decision model, giving yes or no, choice or score answers from text and images
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.