AI Tools
Stable Diffusion 3.5
Stable Diffusion 3.5: preços, capacidades, atualizações e alternativas, lidos nas páginas do próprio desenvolvedor.

Em inglês
Key facts
- Price
- Paid plans: see pricing Read on platform.stability.ai
- Free plan
- No Read on platform.stability.ai
- Platforms
- Web · API
- API
- Yes Read on docs.stability.ai
- Open source
- Yes Read on stability.ai
- Certifications
- SOC 2 Type II Read on trust.stability.ai
- Latest version
- Stable Diffusion 3.5
- Last update
- 12 Aug 2025 Read on stability.ai
- Prices checked
- 26 Oct 2026 Read on platform.stability.ai
The model family creates images in styles such as photography, painting, line art, and 3D. Large, Large Turbo, and Medium variants offer different trade-offs in image generation speed, quality, and customization. Creators, developers, researchers, and businesses can use the model through self-hosting, APIs, or web applications.
The model weights are released under the Stability AI Community License; paid enterprise licensing may apply to organizations above the stated revenue threshold. API generation uses credits. Stability AI says its image and 3D API endpoints will move to Comfy on December 10, 2026, so API users must migrate before then.
- Category
- Image Generation
- Read from the maker’s pages
- 2026-11-18
Company
Features
- Generates images from text prompts
- Offers Large, Large Turbo, and Medium model variants
- Supports image styles including photography, painting, line art, and 3D
- Can be customized and deployed on self-hosted infrastructure
- Can be integrated into custom applications through an API
- Large Turbo generates images in four steps
- Released under the Stability AI Community License
Use cases
- Generate concept art from written prompts
- Create illustrations in different visual styles
- Build image-generation features into an application
- Fine-tune a model for a specific creative workflow
- Run image generation on your own infrastructure
Pricing
Paid plans: see pricing
- Prices checked
- 2026-10-26
Stable Diffusion 3.5 Large
6.5 credits
- 6.5 credits
- 8 billion parameter base model with superior quality and prompt adherence
Stable Diffusion 3.5 Large Turbo
4 credits
- 4 credits
- Turbo variant of Stable Diffusion 3.5 Large, for fast high-quality images
Stable Diffusion 3.5 Medium
3.5 credits
- 3.5 credits
- The 2 and 2.5 billion parameter variants of Stable Diffusion 3.5 respectively
Stable Diffusion 3.5 Flash
2.5 credits
- 2.5 credits
- The distilled version of Stable Diffusion 3.5 Medium, for fast, high-quality images
Capabilities
- Text to image — “SD 3.5 is our most powerful 8 billion parameter base model with superior quality and prompt adherence” source
- Edits images — “Inpaint Use a mask (or alpha channel) to replace anything in an image” source
- Upscales — “Simple, low-cost upscaler to increase image resolution by 4, up to 4 megapixels” source
- Style or character reference — “Style Transfer Apply visual styles from reference images to a target image to maintain consistency across content” source
- Commercial use — “The models are available for commercial and non-commercial use under our permissive Stability AI Community License .” source
- API — “Deploy Stable Diffusion 3.5 on your own infrastructure, integrate it via our API, or start creating now with our web-based applications.” source
Latest updates
- Stability AI and NVIDIA Bring Faster Performance and Simplified Enterprise Deployment with the Stable Diffusion 3.5 NIM
Stability AI launched an NVIDIA NIM microservice for Stable Diffusion 3.5, available at build.nvidia.com.
- API Deprecation Notice
Deprecating the Stable Diffusion 3.0 APIs and automatically upgrading to Stable Diffusion 3.5 APIs at no extra cost.
- Replace Background & Relight
The SD3 and SD3.5 models now support the cfg_scale parameter.
- Stable Diffusion 3.5 Medium & Stable Image Ultra
The endpoint supports sd3.5-medium; Stable Image Ultra is now powered by Stable Diffusion 3.5 Large.
- Stable Diffusion 3.5 Large & Large Turbo
The endpoint supports sd3.5-large and sd3.5-large-turbo in the model parameter.
Where it works
Web · API
Security
Alternatives to Stable Diffusion 3.5
- Stable Diffusion
Stable Diffusion generates images from text prompts and supports image editing, guided generation, and upscaling.
- AUTOMATIC1111
A locally run browser interface for generating and editing images with Stable Diffusion models.
- Fotor AI Image Generator
Fotor creates images from text prompts or reference images, then lets users refine them with prompts and built-in editing tools.
- Flux
FLUX generates and edits images and video from text, images, and reference inputs through Black Forest Labs’ web playground and API.
- Ideogram
Generates and edits images from prompts or references, with text rendering, character consistency, SVG tools and an API.
- Picsart AI Image Generator
Creates images from text prompts using multiple image models, styles, and reference images.
More from Stability AI
- Stable Diffusion
Stable Diffusion generates images from text prompts and supports image editing, guided generation, and upscaling.
Questions about Stable Diffusion 3.5
Is Stable Diffusion 3.5 free?
No. The maker’s pricing page lists no free plan for Stable Diffusion 3.5. Prices checked on 26 Oct 2026.
How much does Stable Diffusion 3.5 cost?
The plans on the maker’s pricing page: Stable Diffusion 3.5 Large (6.5 credits), Stable Diffusion 3.5 Large Turbo (4 credits), Stable Diffusion 3.5 Medium (3.5 credits) and Stable Diffusion 3.5 Flash (2.5 credits). Prices checked on 26 Oct 2026.
Does Stable Diffusion 3.5 have an API?
Yes. The maker’s pages state that Stable Diffusion 3.5 has an API. Read on the maker’s pages on 18 Nov 2026.
Which platforms does Stable Diffusion 3.5 run on?
Stable Diffusion 3.5 runs on Web and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.
Is Stable Diffusion 3.5 open source?
Yes. The maker’s pages state that Stable Diffusion 3.5 is open source. Read on the maker’s pages on 18 Nov 2026.
Is Stable Diffusion 3.5 still available?
Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that Stable Diffusion 3.5 has ended.
What changed recently in Stable Diffusion 3.5?
The latest entry in its maker’s changelog: 12 Aug 2025, “Stability AI and NVIDIA Bring Faster Performance and Simplified Enterprise Deployment with the Stable Diffusion 3.5 NIM”. Before it: 17 Apr 2025, “API Deprecation Notice”. Changelog checked on 18 Nov 2026.
Sources
- https://docs.stability.ai/pricing — Official API pricing in credits, including Stable Diffusion 3.5 model prices and 25 free credits.
- https://stability.ai/stable-image — Product variants, capabilities, and access through self-hosting, API, and web applications.
- https://stability.ai/news-updates/introducing-stable-diffusion-3-5 — Model release, customization, license, and ways to access the model.
- https://stability.ai/news-updates/stability-ai-and-nvidia-bring-faster-performance-and-simplified-enterprise-deployment-with-the-stable-diffusion-35-nim — NVIDIA NIM deployment announcement for Stable Diffusion 3.5.
- https://kb.stability.ai/knowledge-base/transitioning-stability-ai-image-3d-api-endpoints-to-comfyui — States that Stability AI image and 3D API endpoints transition to Comfy on December 10, 2026.