ImageDedicated GPU
Stable Diffusion
Stable Diffusion is still the broadest open image generation family for teams that want checkpoint flexibility, custom fine-tunes, adapters, and private asset pipelines.
Text to imageImage to image
Image
Z Image Turbo on a dedicated GPU for your team
Z Image Turbo is already modeled in the repo as a dedicated image deployment target for teams prioritizing faster image generation and enterprise control.
Inputs
Prompts, optional init image, up to 1488px width and height, webhook callbacks
Outputs
Low-latency text-to-image and image-to-image generations
Why teams deploy Z Image Turbo
Teams choose a dedicated GPU for Z Image Turbo when they need full control over sensitive prompts, proprietary assets, or custom runtime configurations that shared endpoints can't provide.
faster image generation
private image APIs
dedicated enterprise image backends
Deployment details
- Modality
- Image
- Deployment
- Dedicated Z Image Turbo runtime with repo-backed enterprise support
- Starting at
- $1999/month
Supported capabilities
Text to image
Image to image
Up to 2 samples
Webhook-based enterprise delivery
Common use cases
interactive media tools
private creative generation
high-throughput draft rendering
Resources and references
What you get with Enterprise
Dedicated GPU deployment with no shared queue contention
100% private workloads, prompts, and generated outputs
Code access for custom runtimes, adapters, and optimization
Bring-your-own S3 storage for assets, checkpoints, and outputs
Enterprise Deployment
Get a dedicated GPU for this model
Get Z Image Turbo running on a GPU dedicated to your team — with private data flow, full code access, and S3-backed storage for production workloads.
Full privacy for prompts, inputs, and outputs
Code access for custom runtimes and adapters
Your own S3 for checkpoints and generated assets
Dedicated GPU — no shared queue or throttling
Starting at
$1999/month
Scale to higher GPU tiers when you need more VRAM, throughput, or concurrency.
Related models
Explore similar models in the same category for your deployment needs.
ImageDedicated GPU
Stable Diffusion XL
SDXL is the default open model choice for teams that want strong prompt adherence and broad ecosystem support without giving up deployment control.
Text to imageImage to image
ImageDedicated GPU
Stable Diffusion 3.5 Large
Stable Diffusion 3.5 Large is positioned for higher-quality image generation teams that want a modern Stable Diffusion stack on infrastructure they fully control.
Text to imageControlled image workflows
ImageDedicated GPU
Stable Diffusion 3.5 Medium
Stable Diffusion 3.5 Medium is a lighter entry point for teams that want newer Stable Diffusion quality with more practical dedicated GPU cost envelopes.
Text to imageImage-to-image pipelines
ImageDedicated GPU
Stable Diffusion 1.5
SD 1.5 still matters for legacy fine-tunes, mature community checkpoints, and teams that have existing prompt libraries they do not want to migrate yet.
Text to imageImage to image
ImageDedicated GPU
SDXL Turbo
SDXL Turbo is useful when speed matters more than maximal quality and teams want a fast, private image generation runtime on their own dedicated GPU envelope.
Fast text to imageInteractive generation loops
Get Expert Support in Seconds
We're Here to Help.
Want to know more? You can email us anytime at support@modelslab.com