RYLA

ryla_generate_image

Generate Studio-quality images for an existing character with full creative control (scene, outfit, pose, lighting, expression, style). This is the primary, full-featured image tool -- prefer it over ryla_generate_base_image. Character must already exist; use ryla_list_characters to find a characterId. Returns a jobId; poll with ryla_generation_status.

Input Schema

Name	Required	Description
`nsfw`	No	Enable unrestricted fan content generation
`seed`	No	Base seed; each image increments it
`count`	No	Number of images to generate
`scene`	No	Scene preset or description. Required unless templateId is given.
`loraId`	No	LoRA id to use, if not the default for this character
`outfit`	No	Outfit description
`poseId`	No	Pose preset id, e.g. "standing-casual"
`quality`	No	Quality tier: "standard" or "2k" (HD, default), "ultra" or "4k" (4K, costs more credits)
`useLora`	No	Use the character LoRA for face consistency, if trained
`lighting`	No	Lighting preset, e.g. "natural.goldenHour"
`shotType`	No	Camera framing, e.g. "close-up-portrait", "full-body"
`requestId`	No	Optional UUID for this generation intent. Omit it and one is created for you (returned in the result). Pass the SAME id when retrying after an error or a lost response, so the retry is not charged twice.
`expression`	No	Facial expression preset, e.g. "positive.smile"
`templateId`	No	Template id from ryla_list_templates. Fills scene, outfit, pose, style, lighting and aspect ratio from the template; anything you set yourself wins.
`aspectRatio`	No	Image aspect ratio. Required unless templateId is given (then the template ratio is used).
`characterId`	Yes	Character UUID to generate images for
`environment`	No	Environment preset or description
`stylePreset`	No	Visual style preset (default ultraRealistic)
`loraStrength`	No	LoRA strength, 0.1-2.0
`realismStyle`	No	Apply realism post-processing style
`templateMode`	No	With templateId: "exact" (default) keeps the template pose, outfit and background; "inspired" makes a similar but different image.
`promptEnhance`	No	Enable AI prompt enhancement (default true)
`enableFaceSwap`	No	Route through face-swap for the reference image
`referenceMethod`	No	Reference image method (default instantid)
`antiDetectPreset`	No	Anti-detection intensity (default moderate); advanced/maximum require Pro
`socialMediaReady`	No	Apply anti-AI-detection post-processing
`referenceImageUrl`	No	Reference image URL for face consistency (InstantID/PuLID), as an alternative to LoRA
`referenceStrength`	No	Reference image strength, 0.1-1.0

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 21, 2026

changedInput schema / properties / aspectRatio / description

Previous value: -"Image aspect ratio"New value: +"Image aspect ratio. Required unless templateId is given (then the template ratio is used)."

changedInput schema / properties / scene / description

Previous value: -"Scene preset or description"New value: +"Scene preset or description. Required unless templateId is given."

addedInput schema / properties / templateId

Added value: +{
+  "description": "Template id from ryla_list_templates. Fills scene, outfit, pose, style, lighting and aspect ratio from the template; anything you set yourself wins.",
+  "format": "uuid",
+  "type": "string"
+}

addedInput schema / properties / templateMode

Added value: +{
+  "description": "With templateId: \"exact\" (default) keeps the template pose, outfit and background; \"inspired\" makes a similar but different image.",
+  "enum": [
+    "exact",
+    "inspired"
+  ],
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "characterId",
-  "scene",
-  "aspectRatio"
-]New value: +[
+  "characterId"
+]

Changed3 schema fields changedOct 21, 2026

changedInput schema / properties / quality / description

Previous value: -"Quality tier: \"standard\" (HD, default) or \"ultra\" (4K)"New value: +"Quality tier: \"standard\" or \"2k\" (HD, default), \"ultra\" or \"4k\" (4K, costs more credits)"

addedInput schema / properties / quality / enum

Added value: +[
+  "standard",
+  "ultra",
+  "2k",
+  "4k"
+]

addedInput schema / properties / requestId

Added value: +{
+  "description": "Optional UUID for this generation intent. Omit it and one is created for you (returned in the result). Pass the SAME id when retrying after an error or a lost response, so the retry is not charged twice.",
+  "format": "uuid",
+  "type": "string"
+}

First observedSep 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the asynchronous lifecycle (returns a jobId, must be polled) and the precondition that a character must already exist. It does not mention credit consumption (only hinted at in the schema for quality/antiDetectPreset) or any plan gating, so a mutation/cost-bearing operation remains partially opaque.

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?

Four short sentences, front-loaded with purpose, then differentiation, then prerequisite, then lifecycle. Every sentence carries distinct information with no repetition of the schema.

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

Completeness4/5

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

For a 28-parameter tool with no output schema and no annotations, the description covers purpose, sibling routing, prerequisite, and the return/polling contract, which is the essential remaining gap. It leaves out cost/credit implications and plan-gated options (e.g. advanced anti-detect presets), which would be genuinely useful for an expensive generation call.

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% and each parameter already documents enums, defaults, ranges and conditional requirements (scene/aspectRatio vs templateId), so the schema does the heavy lifting. The description only names the creative dimensions generically (scene, outfit, pose, lighting, expression, style) without adding syntax, precedence, or trade-off guidance beyond what the schema states.

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

Purpose5/5

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

States a specific verb ('Generate') and resource ('Studio-quality images for an existing character') plus the controllable dimensions, and explicitly differentiates itself from the sibling ryla_generate_base_image. An agent can distinguish it from ryla_generate_face_swap or ryla_upscale_image without opening a schema.

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

Usage Guidelines5/5

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

Gives an explicit preference rule ('primary, full-featured ... prefer it over ryla_generate_base_image'), a prerequisite ('Character must already exist'), and a discovery path ('use ryla_list_characters to find a characterId'). It also states the follow-up step ('poll with ryla_generation_status'), which is the exact alternative an agent needs after calling.

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

All RYLA tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?