GITNUXSOFTWARE ADVICE
Top 10 Best AI Men Poses Generator of 2026
Ranked comparison of the top ai men poses generator tools for text to image creation, covering Rawshot AI, Leonardo AI, and Midjourney.
How we ranked these tools
Core product claims cross-referenced against official documentation, changelogs, and independent technical reviews.
Analyzed video reviews and hundreds of written evaluations to capture real-world user experiences with each tool.
AI persona simulations modeled how different user types would experience each tool across common use cases and workflows.
Final rankings reviewed and approved by our editorial team with authority to override AI-generated scores based on domain expertise.
Score: Features 40% · Ease 30% · Value 30%
Gitnux may earn a commission through links on this page — this does not influence rankings. Editorial policy
Editor’s top 3 picks
Three quick recommendations before you dive into the full comparison below — each one leads on a different dimension.
Rawshot AI
A dedicated men-posing image generation focus that prioritizes stance/pose outputs over general image creation.
Built for artists and creators who need quick, varied AI-generated men pose references..
Leonardo AI
Editor pickModel and generation parameter routing for consistent, repeatable output runs via API.
Built for fits when teams automate image generation with configuration, model routing, and API pulls..
Midjourney
Editor pickParameter schema for aspect ratio and stylize to control generation behavior.
Built for fits when teams automate prompt-driven visual production with controlled parameters..
Related reading
Comparison Table
This comparison table evaluates AI men pose generator tools across integration depth, including how each platform connects to existing pipelines and content systems via API and extensibility. It also maps the underlying data model and schema, then compares automation and the API surface for provisioning, throughput controls, and configuration options. Admin and governance coverage is scored with RBAC, audit log behavior, and sandbox or tenant isolation controls to show where operational tradeoffs appear.
Rawshot AI
AI image generation for pose creationRawshot AI generates realistic men pose images from prompts for use in creative and visualization workflows.
A dedicated men-posing image generation focus that prioritizes stance/pose outputs over general image creation.
Rawshot AI emphasizes generating men poses that are ready to use as visual references. For an “ai men poses generator” review, it fits because the tool is oriented around creating body positioning outputs you can directly reference or build upon. If your goal is quickly exploring multiple stances and angles, the pose-focused generation is the primary value signal.
A tradeoff is that prompt control can still require iteration to get the exact stance, camera framing, or level of realism you want. A common usage situation is producing a batch of pose options for a storyboard, character sheet, or art-direction reference when you’re working under time constraints.
- +Pose-oriented generation specifically for men figure stance reference
- +Fast iteration for exploring multiple body positions from prompts
- +Useful for art and visualization workflows needing pose variety
- –Exact matching of very specific posture details may require multiple prompt attempts
- –Results quality can vary depending on prompt clarity
- –Primarily optimized for pose outputs rather than full scene generation
Figure artists and illustrators
Generate reference poses for drawings
Faster pose exploration
Character concept artists
Iterate stance options for characters
More refined character sheets
Show 2 more scenarios
Fashion and styling creators
Preview men pose ideas for shoots
Quicker direction decisions
Produces pose-ready visuals to brainstorm stance and presentation before production.
Storyboard artists
Plan action beats with pose references
Clearer scene staging
Generates men pose options to visualize action framing for scene planning.
Best for: Artists and creators who need quick, varied AI-generated men pose references.
Leonardo AI
prompt-to-imageGenerates and edits images from prompts with a controllable workflow for producing consistent men pose variations.
Model and generation parameter routing for consistent, repeatable output runs via API.
Teams use Leonardo AI when they need repeatable visual output across campaigns and require configuration controls beyond a single prompt. The data model is centered on generation inputs like prompt text, model choice, and output settings, with variants captured per run. Integration depth matters because the platform offers an API and tooling for provisioning automated jobs and retrieving results. Admin and governance controls focus on account-level access, with operational traceability supported through run histories and audit-like records in the application experience.
A key tradeoff is that deeper governance like granular RBAC policies, organization-wide audit log export, and sandboxed keys are not as explicitly surfaced for every workflow pattern. Leonardo AI fits usage situations where throughput comes from automated prompt templates and model routing more than from complex enterprise identity governance. It is also a practical choice when teams want to iterate on prompt schemas and generation settings while keeping outputs consistent across multiple batches.
- +API enables programmatic generation and batch throughput
- +Model selection and parameter controls support repeatable outputs
- +Prompt and generation settings map cleanly to a run data model
- +Generation history helps trace outputs back to inputs
- –RBAC granularity and org-wide audit export are limited in visibility
- –Job sandboxing and environment separation are not clearly defined
- –Complex workflow orchestration requires external automation glue
Marketing ops teams
Batch-create ad creatives from templates
Faster creative production cycles
Content production studios
Iterate assets with controlled refinements
Reduced rework during revisions
Show 2 more scenarios
Product teams
Generate UI mock visuals programmatically
More consistent prototype imagery
Use API-driven generation settings to standardize visual outputs for prototypes.
Agency automation engineers
Provision prompt-to-output pipelines
Higher throughput with less manual work
Integrate automation jobs that submit prompts and collect results at scale.
Best for: Fits when teams automate image generation with configuration, model routing, and API pulls.
Midjourney
text-to-imageCreates men pose imagery from text prompts using configurable parameters that support repeatable generation runs.
Parameter schema for aspect ratio and stylize to control generation behavior.
Midjourney’s differentiation comes from prompt parameterization and consistent visual controls exposed through its generation schema. Its automation surface includes an API that enables programmatic image generation, which fits batch workflows and content systems. A strong fit appears when creative operators need repeatable prompt configurations and predictable output settings across many runs.
A key tradeoff is that governance controls for teams rely more on account and workspace structure than on granular in-product RBAC and policy enforcement. Midjourney fits a scenario where a small team automates visual asset generation from structured prompts, then applies review and selection outside the tool. The model is easiest to run at scale when prompts can be templated into a schema that drives throughput.
- +Parameterized prompt controls for repeatable generation settings
- +API access supports scripted and batch image generation
- +Chat workflow supports fast iteration for creative direction
- +Organizational workflow supports team production cycles
- –Automation still requires prompt templating and external orchestration
- –Granular RBAC and policy controls are limited for enterprise governance
- –Audit-ready histories often depend on external logging around API calls
Content operations teams
Batch-create ad visuals from prompt templates
Faster asset production cycles
Product marketing teams
Iterate hero images for landing pages
More iterations per brief
Show 2 more scenarios
Design systems maintainers
Generate concept art aligned to style rules
More consistent concept sets
Prompt configuration enforces style constraints across multiple concept directions.
Agencies with creative ops
Run client-specific prompt pipelines
Lower manual rework
API automation enables provisioning separate prompt configs per client workflow.
Best for: Fits when teams automate prompt-driven visual production with controlled parameters.
Adobe Firefly
prompt-and-editGenerates and refines pose-focused male figures using prompt instructions and editing steps designed for iterative outputs.
Adobe Firefly APIs for automated, parameterized generation tied to Adobe creative asset workflows.
Adobe Firefly serves as an image generation assistant built into Adobe’s creative ecosystem. It supports prompt-driven creation and editing workflows that connect to tools like Photoshop and other Adobe creative apps.
The data model centers on user prompts, asset references, and generation parameters that feed deterministic edits across iterations. Integration depth is strongest inside Adobe workflows, with an extensibility path via Adobe Firefly APIs for automation and external systems.
- +Tight Adobe integration for prompt-based image generation and editing workflows
- +Firefly APIs support programmatic generation for automation and batch throughput
- +Structured parameterization for consistent outputs across repeated runs
- +Asset-aware editing flows using references from the user’s creative workspace
- –Limited depth for non-Adobe pipelines compared with dedicated generator platforms
- –Sandboxing and deterministic controls are narrower than enterprise image factories
- –RBAC and governance features are not as auditable as full enterprise model hubs
- –Extensibility depends on Adobe integration points rather than generic schema control
Best for: Fits when teams need image generation integrated into existing Adobe creative workflows.
Runway
creative automationBuilds pose variation datasets through prompt-driven generation and supports automation-style workflows for repeatable creation.
Job-based generation API with configurable settings for repeatable video output pipelines.
Runway generates AI videos from text prompts and also supports image-to-video and video editing workflows. The integration depth centers on model access through documented endpoints and job-based pipelines that fit into existing automation.
Runway also exposes configuration for generation settings, supports asset input and output handling, and enables workflow orchestration for higher throughput. Admin and governance controls are geared toward team access boundaries, audit visibility, and operational guardrails around who can run and manage generations.
- +API supports prompt jobs with consistent input and output handling
- +Supports image-to-video and text-to-video for controlled pose-driven generation
- +Generation configuration can be scripted for repeatable results
- +Team access boundaries support RBAC-style provisioning for workspaces
- +Audit log support supports traceability for generated assets and actions
- –Pose control depends on input conditioning quality rather than a strict pose schema
- –High-volume throughput needs careful batching and queue management
- –Automation surface emphasizes generation jobs and may require custom glue for complex pipelines
- –Governance controls can lag behind fully custom enterprise workflows
- –Sandboxing for experimentation may require extra operational steps
Best for: Fits when creative teams need API-driven video generation automation with controlled access and auditability.
Krea
pose generationProduces pose variations with prompt conditioning and image generation controls suitable for men pose reference sets.
Project-based asset and prompt organization for repeatable generation and variant tracking.
Krea targets teams generating and editing AI images with a tight prompt-to-output workflow and model controls. The core capability centers on text-to-image and image-to-image generation with adjustable generation parameters and repeatable outputs.
Krea also supports project organization features that help teams standardize prompts, variants, and assets across sessions. Integration depth depends on its automation and API surface, which is the main lever for throughput, governance, and schema-driven workflows.
- +Prompt-to-image workflow supports controlled parameterization per generation request
- +Image-to-image path enables consistent edits from provided source assets
- +Project organization supports repeatable prompt and asset management across runs
- –Integration depth depends on available automation and API endpoints for full pipelines
- –Governance features like RBAC and audit log exposure can constrain enterprise rollout
- –Automation surface may limit fine-grained orchestration for high-throughput batch systems
Best for: Fits when image teams need prompt-controlled generation with repeatable variants and light automation.
Pixlr
editor + AIOffers AI image generation and editing controls that can be used to iterate men pose images with consistent styling.
In-editor AI generation with iterative prompt refinement tied to the editing canvas workflow.
Pixlr centers AI-powered image generation around a browser-first editor workflow that keeps prompts near the canvas. Image outputs can be refined with repeatable prompt edits and layered editing steps inside the same authoring session.
Integration depth is limited to editor-centric extensibility rather than deep system-level provisioning and a formal automation API surface. Automation and governance controls are oriented to workspace authoring features, with fewer explicit hooks for external orchestration.
- +Browser-based editor keeps prompt changes close to the generated output
- +Repeatable prompt edits support iterative variations within the authoring session
- +Layered editing workflow supports post-generation refinement without export hops
- +Project-style organization can reduce prompt sprawl during review cycles
- –No explicit external automation API surface is documented in the core workflow
- –Provisioning controls for AI pipelines are less defined than admin-first services
- –RBAC and audit log visibility for generated content is not clearly specified
- –Throughput controls and sandbox isolation are not presented for programmatic runs
Best for: Fits when teams need authoring-driven AI image generation with minimal engineering integration demands.
Playground AI
prompt-to-imageGenerates images from prompts with configurable settings to support repeatable men pose output batches.
Schema-driven workflow builder that binds tools and I/O fields into reusable, deployable artifacts.
Playground AI targets AI agent and toolchain generation with a schema-driven workflow builder and a reusable component library. The core differentiator is how it models inputs, outputs, and tool bindings so generated artifacts stay consistent across runs.
Integration depth is shaped by an extensibility surface that supports automation and API-based provisioning. Governance relies on project scoping and role boundaries plus operational logs for change tracking and execution review.
- +Schema-first data model keeps generated prompts, tools, and outputs consistent
- +Reusable components reduce duplication across agent and workflow variations
- +Automation and API surface supports provisioning and repeatable deployments
- +Project scoping supports RBAC-style separation between build and execution roles
- +Audit-style logs capture run history and configuration changes
- –Schema constraints can add friction for ad hoc or unstructured workflows
- –Tool binding configuration requires careful versioning to avoid drift
- –Automation paths may demand manual orchestration for multi-service flows
- –Granular governance controls like fine-grained per-tool permissions may be limited
- –Debugging failures across chained tools can require extra instrumentation
Best for: Fits when teams need governed agent generation with API automation and a consistent schema.
Mage Space
image referenceGenerates image references from prompts and supports scene and character consistency for building men pose libraries.
Run-focused API that takes structured pose inputs and returns generated outputs with logged run metadata.
Mage Space generates AI voice and speech-acting poses by turning structured prompts into prompt variants and deliverable outputs in a repeatable workflow. The data model centers on reusable configuration for pose generation, so sequences can be re-run with consistent parameters across projects.
Integration depth is mainly expressed through an automation and API surface for creating runs, passing inputs, and retrieving generated results. Admin and governance are handled through role-based access and audit-friendly operational logging for generated assets and run metadata.
- +Schema-based pose generation inputs for consistent run outputs
- +API-driven provisioning of generation runs and retrieval of results
- +Reusable configuration supports batch regeneration with stable parameters
- +RBAC limits who can edit generation settings and assets
- +Operational logging captures run metadata for traceability
- –More configuration work is required than prompt-only workflows
- –Automation depends on run lifecycle management for higher throughput use cases
- –Moderation and policy controls are limited compared with enterprise AI governance tools
Best for: Fits when teams need API automation for repeatable AI pose generation workflows.
NightCafe Creator
batch generationCreates men pose images from text prompts with generation settings for batch production and style controls.
Style and prompt control workflow for rapid iteration and variant generation.
NightCafe Creator supports AI image generation with a workflow built around prompt inputs, style controls, and curated output handling. Integration depth is primarily centered on web access and shareable outputs rather than an explicit enterprise API or automation toolkit.
The data model is prompt-plus-parameters oriented, with limited visibility into schema fields beyond what is exposed through its generation controls. Extensibility and governance controls are not prominent in publicly documented admin features, which limits use in tightly governed pipelines.
- +Prompt-driven generation with clear UI controls for style and output selection
- +Consistent output management for iterative runs and quick variants
- +Shareable results support lightweight collaboration without extra tooling
- +Works end to end from prompt entry to downloadable images
- –Limited publicly documented API surface for provisioning and automation
- –No clear RBAC or audit log controls for team governance
- –Data model visibility stays tied to UI-exposed parameters
- –Throughput and job orchestration controls are not clearly exposed
Best for: Fits when teams need quick AI image variants with minimal integration and governance overhead.
How to Choose the Right ai men poses generator
This buyer's guide covers AI men pose generators built for stance and body-position reference, including Rawshot AI, Leonardo AI, Midjourney, Adobe Firefly, Runway, Krea, Pixlr, Playground AI, Mage Space, and NightCafe Creator.
The guidance focuses on integration depth, the underlying data model for pose inputs and run outputs, the automation and API surface for repeatable batches, and admin and governance controls like RBAC and audit logging where they exist.
The covered tools span from pose-first generators like Rawshot AI to workflow and schema-driven systems like Playground AI that bind tool I/O into deployable artifacts.
AI men pose generator tools for reference-ready body stance output
An AI men pose generator tool turns prompts and parameters into men figure images focused on stance, body positioning, and pose variety, rather than on full scene realism.
The strongest tools also support repeatable generation runs through structured controls like parameter schemas in Midjourney or run configuration models in Leonardo AI, plus automation paths for batch production. Rawshot AI targets pose-ready male figures directly for figure drawing and concept reference, while Mage Space centers structured pose inputs and returns generated outputs with logged run metadata.
Pose-automation evaluation points for repeatable men stance generation
The deciding factor is whether the tool can produce consistent pose outputs across repeated runs, including how prompts and parameters map into a data model for later traceability.
Integration and governance matter when image pose generation becomes part of a production pipeline, because many tools expose different levels of API automation and different levels of RBAC and audit visibility.
API-run repeatability with model and parameter routing
Leonardo AI provides model selection and generation parameter controls mapped into a run data model, and its API supports programmatic generation and batch throughput. Midjourney adds a parameter schema for aspect ratio and stylize so repeated prompt templates can produce consistent behavior.
Job-based automation with configurable input-output handling
Runway exposes job-based generation through a documented API surface and supports configurable generation settings for repeatable pipelines. Mage Space uses a run-focused API that takes structured pose inputs and returns generated results with operational logging of run metadata.
Schema-first workflow builder and deployable tool bindings
Playground AI uses a schema-driven workflow builder that binds tools and input-output fields into reusable components, which reduces drift across runs. Playground AI also tracks run history and configuration changes with audit-style logs for execution review.
Project organization for standard prompts, variants, and assets
Krea includes project organization that standardizes prompts, variants, and assets across sessions, which helps keep pose libraries consistent over time. Pixlr supports project-style organization inside a browser workflow to reduce prompt sprawl during iterative review cycles.
Pose-first generation tuned for men stance reference
Rawshot AI prioritizes stance and pose outputs for men figure reference, which makes it efficient for iterating multiple body positions from prompts. NightCafe Creator focuses on prompt-plus-style controls and consistent output handling for quick variants, even though its automation surface is limited.
Admin governance controls, RBAC, and audit log traceability
Runway includes audit log support for traceability of generated assets and actions, and it emphasizes team access boundaries with RBAC-style provisioning. Leonardo AI offers API-driven repeatability but has limited RBAC granularity and limited org-wide audit export visibility, which affects enterprise governance setups.
Decision framework for selecting the right pose generator integration depth
Start by deciding whether the pipeline needs pose-first generation quality or whether it needs workflow automation and a governed execution surface. Rawshot AI is designed around men stance reference generation, while Playground AI is designed around schema-driven workflow deployment.
Map the expected input from prompt text to a pose schema
If the generation inputs are already structured as pose parameters, tools like Mage Space and Playground AI fit better because they center structured pose inputs and schema-first I/O. If input is mainly natural-language prompting, Midjourney and Rawshot AI can still work well, but repeatability depends on careful parameterization and prompt templating.
Verify repeatability by testing parameter routing and run history
Leonardo AI supports model selection and parameter controls with generation history that traces outputs back to input settings. Midjourney uses a parameter schema for aspect ratio and stylize, which helps lock generation behavior when prompt templates are reused.
Check the automation surface for batch generation and orchestration
If the system must run at scale through code, prioritize tools with documented API access like Leonardo AI, Midjourney, Runway, and Mage Space. If the system needs multi-step workflow packaging, Playground AI provides schema-driven workflow builder components, while Adobe Firefly ties automation to Adobe creative asset workflows and Firefly APIs.
Align governance expectations with the tool’s RBAC and audit visibility
For team-level audit traceability, Runway includes audit log support for generated assets and actions and supports team access boundaries. For enterprise governance, Leonardo AI has API and repeatable runs but limited RBAC granularity and org-wide audit export visibility, which changes what admin reporting can cover.
Confirm pose fidelity needs versus scene generation scope
If the goal is men pose variety for figure drawing and reference, Rawshot AI is optimized for stance-focused outputs, although exact posture matching can require multiple prompt attempts. If the goal includes pose-linked editing in an existing asset workflow, Adobe Firefly supports prompt-based creation and editing inside Adobe tools, with Firefly APIs for automation.
Who benefits from AI men pose generators built for repeatable reference libraries
Different organizations need different control surfaces, because pose generation can be a creative ideation step or a governed production system.
The tool’s best-fit use case maps directly to its automation and data model approach.
Artists building men pose reference sets from prompt iterations
Rawshot AI fits this workflow because it is optimized for men-posing image generation that prioritizes stance and body-position variety from prompts. NightCafe Creator also fits quick variant generation when the main requirement is prompt and style control with consistent output management.
Teams automating batch image generation with repeatable run configuration
Leonardo AI fits because its API supports programmatic generation, batch throughput, and model and parameter routing tied to a run data model. Midjourney fits when batch production relies on parameterized prompt templates and API-access scripted runs.
Creative pipelines that require governed job execution and traceable actions
Runway fits teams that need job-based generation APIs for controlled pipelines and audit log support for traceability of generated assets and actions. Mage Space fits teams that want a run-focused API with structured pose inputs plus operational logging for run metadata.
Studios standardizing prompts and variants across projects
Krea fits because project organization supports repeatable prompt and asset management with variants tracked across sessions. Pixlr fits when the standardization work happens inside a browser authoring workflow that keeps prompt edits close to the canvas.
Engineering teams packaging pose generation as schema-driven workflows and reusable tool bindings
Playground AI fits when the requirement is a schema-first workflow builder that binds tools and I/O fields into reusable, deployable artifacts with audit-style logs. This approach reduces drift across chained tools compared with ad hoc prompt-only workflows.
Failure modes when selecting and deploying AI men pose generators
Misalignment between pose fidelity goals and automation expectations causes most failed deployments.
The reviewed tools also show predictable gaps in governance, sandboxing, and orchestration that can break pipelines when they are assumed to exist.
Choosing a pose-first tool without verifying how exact posture matching will be achieved
Rawshot AI prioritizes stance-focused outputs, but exact matching of very specific posture details can require multiple prompt attempts. A corrective approach is to combine Rawshot AI prompt iterations with parameterized control in Midjourney or run-traceable configuration in Leonardo AI.
Assuming full enterprise governance when RBAC and audit export are limited
Leonardo AI supports API-driven repeatability, but RBAC granularity and org-wide audit export visibility are limited. Runway is a better fit for traceability because it includes audit log support for generated assets and actions.
Building a batch pipeline around a tool that lacks a documented external automation API surface
Pixlr is browser-first and does not present an explicit external automation API surface in the core workflow, and NightCafe Creator has limited publicly documented API for provisioning and automation. A corrective choice is to use Leonardo AI, Midjourney, Runway, or Mage Space when the pipeline must run through code.
Underestimating orchestration effort for multi-step workflows
Midjourney offers API access, but automation still requires prompt templating and external orchestration for complex pipelines. Playground AI reduces orchestration work by using schema-driven workflow builder components and reusable tool bindings, while Runway provides job-based generation pipelines that fit orchestration patterns.
How We Selected and Ranked These Tools
We evaluated Rawshot AI, Leonardo AI, Midjourney, Adobe Firefly, Runway, Krea, Pixlr, Playground AI, Mage Space, and NightCafe Creator by scoring features, ease of use, and value from the provided capability details and stated constraints in each tool’s profile. Features carry the most weight at forty percent, while ease of use and value each account for thirty percent in the overall score. This criteria-based scoring emphasizes integration depth, automation and API surface, and how repeatable runs map into a traceable data model because men pose generation often needs repeatable reference libraries.
Rawshot AI stood apart because it is dedicated to men-posing image generation that prioritizes stance and pose outputs, and that fit raised its feature and ease-of-use scores more than tools that focus on general image or broader scene generation.
Frequently Asked Questions About ai men poses generator
Which men-poses generator supports the most consistent stance output for repeated runs?
Which tool offers the strongest API and automation surface for integrating men pose generation into pipelines?
How do teams connect men-poses generation to existing creative tooling without building a custom workflow?
What integration approach works best when an automation layer needs structured inputs and predictable outputs?
Which platform provides the clearest admin controls and audit visibility for team access boundaries?
How can data migration work when switching from one men-poses workflow to another?
What technical workaround helps when image-to-video or higher-throughput workflows are required from pose inputs?
Why do some teams see inconsistent pose results when using chat-based generators, and how can they reduce variance?
Which tool is better suited for variant tracking of prompts and pose outputs across sessions?
Conclusion
After evaluating 10 tools, Rawshot AI stands out as our overall top pick — it scored highest across our combined criteria of features, ease of use, and value, which is why it sits at #1 in the rankings above.
Use the comparison table and detailed reviews above to validate the fit against your own requirements before committing to a tool.
Tools reviewed
Primary sources checked during evaluation.
Referenced in the comparison table and product reviews above.
Keep exploring
Comparing two specific tools?
Software Alternatives
See head-to-head software comparisons with feature breakdowns, pricing, and our recommendation for each use case.
Explore software alternatives→Need a personal recommendation?
Software Advisory Service
Skip months of vendor evaluation. Our analysts recommend the right tool for your business in 2–4 weeks.
Talk to an analyst →FOR SOFTWARE VENDORS
Not on this list? Let’s fix that.
Our best-of pages are how many teams discover and compare tools in this space. If you think your product belongs in this lineup, we’d like to hear from you—we’ll walk you through fit and what an editorial entry looks like.
Apply for a ListingWHAT THIS INCLUDES
Where buyers compare
Readers come to these pages to shortlist software—your product shows up in that moment, not in a random sidebar.
Editorial write-up
We describe your product in our own words and check the facts before anything goes live.
On-page brand presence
You appear in the roundup the same way as other tools we cover: name, positioning, and a clear next step for readers who want to learn more.
Kept up to date
We refresh lists on a regular rhythm so the category page stays useful as products and pricing change.