BlitzReels Video Editor

Generate Image

generation_image_create

Idempotent

Queue an AI image generation into the BlitzReels media library. Spends AI credits and returns a job to poll with generation_jobs_get.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`model`	No	Image model. Call generation_options_list for costs.	fal-ai/nano-banana-2
`prompt`	Yes	What the image should show (8-5000 characters).
`folderId`	No	Optional media library folder ID.
`resolution`	No	Native image resolution. Call generation_options_list for model support and resolution pricing. Unsupported settings are rejected.
`aspectRatio`	No	Output aspect ratio.	1:1
`workspaceId`	No	Optional workspace ID. Defaults to the user's default workspace. UUID string.
`enhancePrompt`	No	Enhance using BlitzReels model grammar and actual input context.
`idempotencyKey`	No	Retry key. Reuse only with identical inputs.
`referenceAssetIds`	No	Ordered image references. Model-specific limits are listed in generation_options_list; unsupported references fail.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`generation`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 8, 2026

changedInput schema / properties / model / enum

Previous value: -[
-  "fal-ai/gpt-image-1",
-  "fal-ai/gpt-image-1.5",
-  "fal-ai/gpt-image-2",
-  "xai/grok-imagine-image-2.0",
-  "fal-ai/bytedance/seedream/v5/lite/text-to-image",
-  "bytedance/seedream/v5/pro/text-to-image",
-  "fal-ai/krea-2/turbo",
-  "fal-ai/krea/v2/medium/turbo/text-to-image",
-  "fal-ai/krea/v2/medium/text-to-image",
-  "fal-ai/nano-banana-2",
-  "google/nano-banana-2-lite",
-  "fal-ai/nano-banana-pro"
-]New value: +[
+  "fal-ai/gpt-image-1",
+  "fal-ai/gpt-image-1.5",
+  "fal-ai/gpt-image-2",
+  "fal-ai/gpt-image-2.5-flare",
+  "fal-ai/gpt-image-2.5-sunburst",
+  "xai/grok-imagine-image-2.0",
+  "fal-ai/bytedance/seedream/v5/lite/text-to-image",
+  "bytedance/seedream/v5/pro/text-to-image",
+  "fal-ai/krea-2/turbo",
+  "fal-ai/krea/v2/medium/turbo/text-to-image",
+  "fal-ai/krea/v2/medium/text-to-image",
+  "fal-ai/nano-banana-2",
+  "google/nano-banana-2-lite",
+  "fal-ai/nano-banana-pro"
+]

Changed4 schema fields changedSep 5, 2026

addedInput schema / properties / enhancePrompt

Added value: +{
+  "default": false,
+  "description": "Enhance using BlitzReels model grammar and actual input context.",
+  "type": "boolean"
+}

changedInput schema / properties / referenceAssetIds / description

Previous value: -"Up to 4 existing image asset IDs to use as style or subject references."New value: +"Ordered image references. Model-specific limits are listed in generation_options_list; unsupported references fail."

changedInput schema / properties / referenceAssetIds / maxItems
```
Previous value: -4New value: +14
```

addedInput schema / properties / resolution

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "0.5k",
+        "1k",
+        "2k",
+        "4k"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Native image resolution. Call generation_options_list for model support and resolution pricing. Unsupported settings are rejected."
+}

Changed1 schema field changedAug 25, 2026

changedInput schema / properties / model / enum

Previous value: -[
-  "fal-ai/gpt-image-1",
-  "fal-ai/gpt-image-1.5",
-  "fal-ai/gpt-image-2",
-  "xai/grok-imagine-image-2.0-preview",
-  "fal-ai/bytedance/seedream/v5/lite/text-to-image",
-  "bytedance/seedream/v5/pro/text-to-image",
-  "fal-ai/krea-2/turbo",
-  "fal-ai/krea/v2/medium/turbo/text-to-image",
-  "fal-ai/krea/v2/medium/text-to-image",
-  "fal-ai/nano-banana-2",
-  "google/nano-banana-2-lite",
-  "fal-ai/nano-banana-pro"
-]New value: +[
+  "fal-ai/gpt-image-1",
+  "fal-ai/gpt-image-1.5",
+  "fal-ai/gpt-image-2",
+  "xai/grok-imagine-image-2.0",
+  "fal-ai/bytedance/seedream/v5/lite/text-to-image",
+  "bytedance/seedream/v5/pro/text-to-image",
+  "fal-ai/krea-2/turbo",
+  "fal-ai/krea/v2/medium/turbo/text-to-image",
+  "fal-ai/krea/v2/medium/text-to-image",
+  "fal-ai/nano-banana-2",
+  "google/nano-banana-2-lite",
+  "fal-ai/nano-banana-pro"
+]

Changed1 schema field changedAug 12, 2026

changedInput schema / properties / model / enum

Previous value: -[
-  "fal-ai/gpt-image-1",
-  "fal-ai/gpt-image-1.5",
-  "fal-ai/gpt-image-2",
-  "fal-ai/bytedance/seedream/v5/lite/text-to-image",
-  "bytedance/seedream/v5/pro/text-to-image",
-  "fal-ai/krea-2/turbo",
-  "fal-ai/krea/v2/medium/turbo/text-to-image",
-  "fal-ai/krea/v2/medium/text-to-image",
-  "fal-ai/nano-banana-2",
-  "google/nano-banana-2-lite",
-  "fal-ai/nano-banana-pro"
-]New value: +[
+  "fal-ai/gpt-image-1",
+  "fal-ai/gpt-image-1.5",
+  "fal-ai/gpt-image-2",
+  "xai/grok-imagine-image-2.0-preview",
+  "fal-ai/bytedance/seedream/v5/lite/text-to-image",
+  "bytedance/seedream/v5/pro/text-to-image",
+  "fal-ai/krea-2/turbo",
+  "fal-ai/krea/v2/medium/turbo/text-to-image",
+  "fal-ai/krea/v2/medium/text-to-image",
+  "fal-ai/nano-banana-2",
+  "google/nano-banana-2-lite",
+  "fal-ai/nano-banana-pro"
+]

First observedAug 5, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With annotations already covering readOnly=false, idempotent=true, openWorld=true, and destructive=false, the description still adds real behavioral context: it is asynchronous (queued, not synchronous), it consumes credits, and the result must be polled via generation_jobs_get. It stops short of stating credit costs, failure modes, or idempotency semantics for the idempotencyKey.

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?

Two short sentences with zero filler, front-loading the action and destination before the async/credit implications. Every clause earns its place.

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?

An output schema exists, so return-shape detail is unnecessary, and the description correctly focuses on the async job + polling workflow and the credit cost. It is nearly complete; the only omitted nuances (cost lookup, idempotencyKey retry semantics) are delegated to the schema and generation_options_list.

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 every parameter (model, prompt, resolution, referenceAssetIds, idempotencyKey, etc.) is already documented in the schema, including pointers to generation_options_list for costs and model support. The description adds no parameter-level meaning beyond what the schema provides, so the baseline 3 applies.

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 and resource ('Queue an AI image generation'), names the destination ('BlitzReels media library'), and is trivially distinguishable from sibling generators like generation_video_create, generation_music_create, and generation_voiceover_create by media type.

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

Usage Guidelines4/5

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

Gives clear context and names the follow-up tool explicitly ('returns a job to poll with generation_jobs_get'), which routes the agent through the async workflow. It does not state when to prefer this over other generation_* siblings or note prerequisites, but the usage context is unambiguous.

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

All BlitzReels Video Editor 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?