xpay✦ Media Studio

stability_ai_sdxl

SDXL — high-resolution image generation with fine-grained control

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mask`	No	Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
`seed`	No	Random seed. Leave blank to randomize the seed
`image`	No	Input image for img2img or inpaint mode
`width`	No	Width of output image
`height`	No	Height of output image
`prompt`	No	Input prompt	An astronaut riding a rainbow unicorn
`refine`	No	Which refine style to use	no_refiner
`scheduler`	No	scheduler	K_EULER
`lora_scale`	No	LoRA additive scale. Only applicable on trained models.
`num_outputs`	No	Number of images to output.
`refine_steps`	No	For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
`guidance_scale`	No	Scale for classifier-free guidance
`apply_watermark`	No	Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
`high_noise_frac`	No	For expert_ensemble_refiner, the fraction of noise to use
`negative_prompt`	No	Input Negative Prompt
`prompt_strength`	No	Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
`replicate_weights`	No	Replicate LoRA weights to use. Leave blank to use the default weights.
`num_inference_steps`	No	Number of denoising steps
`disable_safety_checker`	No	Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)

TDQS

C2.7/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of disclosing behavioral traits, yet it offers only a vague 'fine-grained control' claim. It fails to mention key behaviors such as the default safety checker, watermarking, inpainting/img2img modes, or the effect of prompt_strength on information destruction., leaving the agent without critical operational knowledge.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. It immediately identifies the tool and its primary value proposition without redundancy, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a complex tool with 19 parameters, no annotations, and no output schema, yet the description provides almost no contextual information. It doesn't explain the various generation modes, safety/watermark controls, return format, or any limitations, making it insufficient for an agent to use the tool effectively in varied scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds no parameter information, but the schema already provides detailed explanations for all 19 parameters, including mode-specific fields like mask and prompt_strength. The description neither enhances nor detracts from parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that this tool generates high-resolution images with fine-grained control, and the name 'SDXL' identifies the specific model. However, it doesn't distinguish this tool from sibling image-generation tools like black_forest_labs_flux_dev or ideogram_v3, missing an opportunity to highlight unique capabilities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. There is no mention of appropriate use cases, exclusions, or context that would help an agent choose between SDXL and sibling tools, leaving the agent to infer usage from the name and schema alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All xpay✦ Media Studio tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.2/5.0

Disambiguation2/5

Six of eight tools are for image generation, with overlapping capabilities and only subtle differentiators (speed, quality, text rendering). An agent cannot easily determine which model to use for a generic image generation request, leading to high ambiguity.

Naming Consistency5/5

All tool names follow the same snake_case pattern using provider_model format (e.g., black_forest_labs_flux_pro, stability_ai_sdxl). The convention is uniform across the entire set, making it predictable and easy to parse.

Tool Count4/5

The count of 8 tools is within the ideal range for a media studio, but the heavy redundancy of image generation models makes the set slightly bloated. Still, the overall scope is clear and manageable.

Completeness4/5

The tool surface covers the primary media generation modalities—image, video, and text-to-speech—which aligns with the 'Media Studio' purpose. Minor gaps exist (e.g., no image editing or audio-to-text), but core generation workflows are well covered.

Resources

Need Help?