stable-diffusion-3.5-large

stabilityai/stable-diffusion-3_5-large

NVIDIA Build Card

Stable Diffusion 3.5 is a popular text-to-image generation model

Context Length

Not published

Input Pricing

Not published

Output Pricing

Not published

Recent Latency

No probes

Model Architecture & Limits

Canonical IDstabilityai/stable-diffusion-3_5-large

Publisher / Originatorstabilityai

Model FamilyCosmos

ArchitectureDiffusion Transformer (DiT)

Context Window LimitNot published

Max Output TokensNot published

Endpoint Protocolnim-custom

Capabilities & Modal Surfaces

Chat Conversation✕ No

Tool / Function Calling✕ No

Reasoning / Thinking✕ No

Structured Output (JSON)✕ No

Vision / Multimodal✓ Yes

Audio Processing✕ No

License & Restrictions

GOVERNING TERMS: The trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf), and use of the Cosmos model is governed by the [NVIDIA Community Model License Agreement](https://www.n

Commercial and research use permitted under governing model and API terms.