AetherWave Studio

Edit image with AI (I2I)

aetherwave_edit_image

Edits an existing image guided by a text prompt. Pass a public imageUrl plus a prompt describing the change ("add a moon to the sky", "swap the background for a neon city", "make it look like a comic panel"). Submits, polls, and returns the edited image URL(s). Default model is 'grok-imagine-i2i' (10 cr, one image, ~15-30s, best cost-to-quality on standard edits). Other I2I-capable models: 'seedream-v4-edit', 'wan-2.5-spicy-i2i', 'flux-kontext-pro', 'qwen-image-edit', 'gpt-image-1.5-i2i' (slow, ~5min). Use list_image_models for full lineup. Note: source URLs with spaces or parentheses may fail upstream; prefer clean URLs.

Model selection guide for edits

Default: grok-imagine-i2i (10 cr, one image, fast ~15-30s, strong general-purpose edit quality).

Pick a different model when:

Need a single deterministic output, or 4K resolution -> seedream-v4-edit (7 cr per image, supports 1K/2K/4K, multi-image up to 6)
Subtle edits / preserve composition / character consistency -> flux-kontext-pro or flux-kontext-max
NSFW edits -> wan-2.5-spicy-i2i
Highest quality, time is not a concern (~5 min OK) -> gpt-image-1.5-i2i (6 cr medium, 31 cr high) or grok-imagine-quality-i2i (14 cr)

If the user simply says "edit this image" with no other signal, default to grok-imagine-i2i.

Returns within ~45 s. If the result has state "running" the job is still rendering: poll aetherwave_get_job with the returned taskId and kind every ~10 s. Pass wait:true ONLY if your MCP client permits tool calls longer than 60 s (most do not). Pass async:true to get the taskId back immediately without waiting.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>",
      "imageUrl": "<imageUrl>"
    },
    "name": "aetherwave_edit_image"
  }
}

Input Schema

Name	Required	Description
`wait`	No	Block until the job finishes (up to the tool's full budget, 6-15 minutes). ONLY if your MCP client permits tool calls longer than 60 s; most abandon the call at 60 s and lose the taskId. Default false: return within ~45 s and hand back a taskId if still running.
`async`	No	Submit and return the taskId immediately without polling at all. Then poll aetherwave_get_job(taskId, kind).
`model`	No	Model ID. Defaults to 'grok-imagine-i2i' (10 cr, one image). Other options: 'seedream-v4-edit', 'wan-2.5-spicy-i2i', 'flux-kontext-pro', 'qwen-image-edit', 'gpt-image-1.5-i2i', 'grok-imagine-quality-i2i'. Use list_image_models for the full list.
`prompt`	Yes	Text description of the edit (e.g. 'replace the sky with sunset clouds').
`quality`	No	Quality preset for models that support it (e.g. GPT Image 2).
`imageUrl`	Yes	Public URL of the source image to edit. Must be a real, fetchable URL.
`maxImages`	No	Number of variations to return, billed per image. Only `seedream-v4-edit` (1-6) and `qwen-image-edit-plus` (1-3) take a count; every other model ignores it.
`resolution`	No	Output resolution. Tiered-pricing models accept '1K' / '2K'.
`aspectRatio`	No	Output aspect ratio (e.g. '1:1', '16:9'). Defaults to the source ratio for most models.
`renderingSpeed`	No	Rendering speed preset for models that support it.
`negative_prompt`	No	What to avoid in the output (supported by some models).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 1, 2026

changedInput schema / properties / maxImages / description

Previous value: -"Number of variations to return for multi-output models."New value: +"Number of variations to return, billed per image. Only `seedream-v4-edit` (1-6) and `qwen-image-edit-plus` (1-3) take a count; every other model ignores it."

changedInput schema / properties / maxImages / maximum
```
Previous value: -8New value: +6
```

Changed1 schema field changedOct 4, 2026

changedInput schema / properties / model / description

Previous value: -"Model ID. Defaults to 'grok-imagine-i2i' (6 cr, one image). Other options: 'seedream-v4-edit', 'wan-2.5-spicy-i2i', 'flux-kontext-pro', 'qwen-image-edit', 'gpt-image-1.5-i2i', 'grok-imagine-quality-i2i'. Use list_image_models for the full list."New value: +"Model ID. Defaults to 'grok-imagine-i2i' (10 cr, one image). Other options: 'seedream-v4-edit', 'wan-2.5-spicy-i2i', 'flux-kontext-pro', 'qwen-image-edit', 'gpt-image-1.5-i2i', 'grok-imagine-quality-i2i'. Use list_image_models for the full list."

Changed3 schema fields changedOct 1, 2026

addedInput schema / properties / async

Added value: +{
+  "description": "Submit and return the taskId immediately without polling at all. Then poll aetherwave_get_job(taskId, kind).",
+  "type": "boolean"
+}

changedInput schema / properties / model / description

Previous value: -"Model ID. Defaults to 'grok-imagine-i2i' (3 cr/image effective, 2 outputs). Other options: 'seedream-v4-edit', 'wan-2.5-spicy-i2i', 'flux-kontext-pro', 'qwen-image-edit', 'gpt-image-1.5-i2i', 'grok-imagine-quality-i2i'. Use list_image_models for the full list."New value: +"Model ID. Defaults to 'grok-imagine-i2i' (6 cr, one image). Other options: 'seedream-v4-edit', 'wan-2.5-spicy-i2i', 'flux-kontext-pro', 'qwen-image-edit', 'gpt-image-1.5-i2i', 'grok-imagine-quality-i2i'. Use list_image_models for the full list."

addedInput schema / properties / wait

Added value: +{
+  "description": "Block until the job finishes (up to the tool's full budget, 6-15 minutes). ONLY if your MCP client permits tool calls longer than 60 s; most abandon the call at 60 s and lose the taskId. Default false: return within ~45 s and hand back a taskId if still running.",
+  "type": "boolean"
+}

First observedJun 20, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations: exact credit costs (10 cr), latency (~15-30s, returns within ~45s), per-image billing for variations, the polling contract (get_job every ~10s with taskId+kind), and the 60s client-timeout caveat for wait:true. Also discloses a real failure mode (source URLs with spaces/parentheses may fail upstream).

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

Conciseness4/5

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

Well front-loaded: the core action, then the default, then a scannable model-selection block, then the polling contract. Slightly long, with the model list appearing both in prose and in the schema's model description, but no sentence is wasted on padding.

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

Completeness5/5

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

For a non-idempotent, billed, long-running generation tool with no output schema, the description covers what comes back (edited image URL(s) or a taskId), how to resume the job, cost, and timing — everything needed to call it correctly.

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

Parameters4/5

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

Schema coverage is already 100%, so the baseline is 3; the description adds meaningful selection semantics on top — which models accept maxImages/resolution, which are slow (~5 min), and cost tiers per model — that the schema's flat enum list doesn't convey. The wait/async distinction is reinforced rather than merely restated.

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 ('Edits an existing image guided by a text prompt') and gives concrete prompt examples that pin down the operation. The 'I2I' framing and the imageUrl requirement make it clearly distinct from the text-to-image generate_image sibling without the agent needing to open either schema.

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?

A full model-selection rubric is provided with an explicit default-and-fallback rule ('If the user simply says "edit this image"... default to grok-imagine-i2i'), and alternatives like list_image_models are named. What's missing is when NOT to use this tool at all — e.g. versus upscale_image, reframe_image, or generate_image — which is left implicit.

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

All AetherWave Studio 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?