AI Image Generator by RunComfy
Inceptions AI INC v1.0.5
Create images across AI models
From the developer
Declared capabilities
- Generate images from text
- Create images from references
- Create character and scene variations
Declared limitations
- N1: prompt drafting only.
- N2: inaccessible private reference.
- N3: insufficient balance is not permission for a digital-credit purchase.
Not specified in the available declarations: pricing & account requirements.
Onboarding example
Create a watercolor landscape of a mountain village at sunrise.
Sources & dates
Developer declarations; not independently tested. Listing last checked Nov 18, 2026. Package observed Nov 18, 2026.
Description
From the marketplace listing
AI Image Generator by RunComfy creates images from text and supported reference images using models available through RunComfy, including FLUX, Nano Banana and Qwen image models. What you can do: - Turn a written description into illustrations, concept art and other still images. - Use a reference image with a compatible model to create a new composition. - Create character or scene variations, with checks for the details you want to preserve. - Choose available image dimensions and model options, then retrieve the result or check an existing generation. Connect a RunComfy account to use the generation tools. Generations use your RunComfy account balance. Available models and settings depend on the current catalog and the selected model. Reference images must be available through an accessible HTTPS link. If a chat attachment cannot be passed to the model, the plugin asks for a usable image link before generating. Generated variations can change identity, text or fine details; inspect the result before using it.
Language: English · Automatically detected from descriptions.
Changes
No changes recorded yet. Follow this plugin to keep track of future changes.
First seen Nov 18, 2026. Last seen Nov 18, 2026.
Similar plugins
Finding similar plugins… Results will appear here automatically.
Browse plugins →Keywords
Files & skills
File archives
Skill instructions
character-scene-variations8.76 KB
--- name: character-scene-variations description: Generate requested character or scene variations as still images with RunComfy, using a written concept or an accessible reference. Use for a requested series or alternate scenes; do not promise identical characters or start unrequested paid variants. --- # Character and scene variations Generate the user's requested alternatives while making continuity limits clear. Respond in the user's language. This workflow uses only the RunComfy MCP tools described here and requires no CLI or cross-plugin skill. Use only this plugin’s current host-provided tool definitions: actual names, descriptions, typed outer arguments and allowed model scope. Old published caches and conditional names in previous packages do not establish current availability or its limits. If current definitions cannot be verified, report an unverified connection binding, not that RunComfy lacks the product capability. If verified definitions offer no compatible operation, explain the connection-specific limitation before spending. Do not assume a discovery tool, switch endpoints, invent operations or bypass the connection through workflow/deployment execution. ## Define the approved series Separate the shared subject/appearance/style from the changes in each scene. Use an existing user brief when sufficient; clarify only missing constraints that change the intended series. Establish the requested count, scenes and budget. Do not manufacture extra variations to promote more runs. For text-only concepts, a series can reuse a concise appearance/style description. This does not create a persistent character model. For a reference, keep the original reference(s) and their role explicit across the series. Character training and custom LoRA creation are outside this image-generation workflow. For reference media, use externally fetchable HTTPS URLs that an unauthenticated GET can retrieve. When the host supplies such a URL for the user’s attachment and access is authorized for this task, use it directly; do not request another upload. Local paths, `file://`, internal attachment/sandbox IDs and data URIs cannot be passed to the Model API. Without a usable URL, explain the limit and request a direct link or a genuinely available, authorized host upload. These MCP tools do not upload arbitrary media: do not invent hosting, publish private media without permission, embed account credentials in URLs or repurpose training uploads. When a reference is used, confirm it is a still image: a known HTML page, video or audio URL is not a valid substitute. Resolve an ambiguous media type before a paid request; do not invent conversion or claim an uninspected URL was verified. ## Exposed operation and series routing 1. For a text-led series, select a currently exposed image operation and model that fit the shared brief and each scene. Use `generate_image` when the current host exposes a compatible definition, following its actual declared arguments and allowed model scope. Reusing text does not create a persistent identity model. 2. For reference-led variants, select a current operation and model whose schemas accept every essential reference and its role. Do not replace image references with a text guess or route them through a text-only legacy tool. Read actual seed, ratio and output-count controls; none guarantees identical identity. 3. Use an exposed `get_model` operation when available to read details and pricing for the exact selected model supported by the matched operation. Validate the current outer tool schema and that model’s input schema together; model metadata cannot expand the operation’s allowed scope. A fixed-model operation cannot be retargeted by adding another model ID. Map each authorized variation and real reference to its own declared arguments and output/request count. ## Cost and single submission per request Use model-returned `base_price_usd` and `price_unit` to explain an estimate for the whole ap
Preview of the first 4,000 characters. Read full instructions →
reference-guided-image8.58 KB
--- name: reference-guided-image description: Create a new still image guided by user-provided reference images with RunComfy, such as a reference-led composition or visual concept. Requires remotely accessible image inputs; does not provide automatic attachment hosting or guarantee exact identity preservation. --- # Reference-guided image Create the requested still using reference-capable RunComfy models exposed by this plugin. Respond in the user's language. All steps here use MCP tools; do not assume a CLI, uploader or another plugin skill exists. Use only this plugin’s current host-provided tool definitions: actual names, descriptions, typed outer arguments and allowed model scope. Old published caches and conditional names in previous packages do not establish current availability or its limits. If current definitions cannot be verified, report an unverified connection binding, not that RunComfy lacks the product capability. If verified definitions offer no compatible operation, explain the connection-specific limitation before spending. Do not assume a discovery tool, switch endpoints, invent operations or bypass the connection through workflow/deployment execution. ## Resolve the reference input first Identify which reference supplies the subject, which supplies a style or composition, what should change, and what the user wants preserved. Keep reference order explicit. Obtain the desired output count and framing without adding a batch the user did not request. For reference media, use externally fetchable HTTPS URLs that an unauthenticated GET can retrieve. When the host supplies such a URL for the user’s attachment and access is authorized for this task, use it directly; do not request another upload. Local paths, `file://`, internal attachment/sandbox IDs and data URIs cannot be passed to the Model API. Without a usable URL, explain the limit and request a direct link or a genuinely available, authorized host upload. These MCP tools do not upload arbitrary media: do not invent hosting, publish private media without permission, embed account credentials in URLs or repurpose training uploads. When a reference is used, confirm it is a still image: a known HTML page, video or audio URL is not a valid substitute. Resolve an ambiguous media type before a paid request; do not invent conversion or claim an uninspected URL was verified. Treat signed asset URLs as access-bearing data: pass them only to the selected model for this task and avoid repeating them in prose unnecessarily. ## Match an exposed image operation 1. Select a currently exposed image operation that supports the actual source/reference images and requested edit or composition. Use `generate_image` when the current host exposes a compatible definition, following its actual declared arguments and allowed model scope. A text-only operation cannot substitute for a required reference input. 2. Inspect the matched operation and supported model schemas for image fields, reference count/order, dimensions, output controls and any requested mask or style controls. Use an exposed `get_model` operation when available to read details and pricing for the exact selected model supported by the matched operation. Validate the current outer tool schema and that model’s input schema together; model metadata cannot expand the operation’s allowed scope. A fixed-model operation cannot be retargeted by adding another model ID. 3. Build only that exposed operation’s declared arguments from the actual subject/style/composition references and their roles. Do not drop an essential reference, invent an input property or substitute text-only generation. Explain a missing control before considering a different user-authorized scope. ## Authorize and generate Use returned `base_price_usd`/`price_unit` when present to explain the expected cost basis and the number of paid requests. Reference count, dimensions or other options may affect price; label an estimate honestly. `get_b
Preview of the first 4,000 characters. Read full instructions →
text-to-image8.45 KB
--- name: text-to-image description: Generate a new still image from a text brief with RunComfy hosted models, including illustrations, posters and visual concepts. Use for requested image creation without a source image; writing a prompt alone does not authorize generation. --- # Text to image Turn the user's brief into an actual image using this plugin's RunComfy MCP tools. Respond in the user's language. This skill is self-contained and requires no CLI, local software or other plugin skill. Use only this plugin’s current host-provided tool definitions: actual names, descriptions, typed outer arguments and allowed model scope. Old published caches and conditional names in previous packages do not establish current availability or its limits. If current definitions cannot be verified, report an unverified connection binding, not that RunComfy lacks the product capability. If verified definitions offer no compatible operation, explain the connection-specific limitation before spending. Do not assume a discovery tool, switch endpoints, invent operations or bypass the connection through workflow/deployment execution. ## Inputs and routing Use the requested subject, style, framing, aspect ratio, exact visible text and output count. Ask only for information that materially affects the request or is required by the selected model. Preserve an explicitly chosen model when available. For a source-image request, a reference-capable model and reachable image URL are required; do not silently replace reference guidance with text-only generation. If the user supplies reference media for a supported reference workflow, use its actual authorized host HTTPS URL when available; do not require another upload or publish a private attachment. Otherwise explain the need for a usable direct link or an actually available authorized upload feature. Text-only generation needs no media URL. 1. Select a currently exposed image operation and supported model that fit the text brief and requested controls. Use `generate_image` when the current host exposes a compatible definition, following its actual declared arguments and allowed model scope. A text-only operation cannot accept a required source image. 2. Read the current typed outer arguments and selected model schema for prompt, image size, seed and optional controls. Use a model selector or nested input object only where the current operation declares it. Use an exposed `get_model` operation when available to read details and pricing for the exact selected model supported by the matched operation. Validate the current outer tool schema and that model’s input schema together; model metadata cannot expand the operation’s allowed scope. A fixed-model operation cannot be retargeted by adding another model ID. 3. Construct only the supported arguments from the brief, preserving an explicitly selected model and requested output count. Resolve unsupported requirements without silently changing the model or task. A prompt or estimate request alone never starts generation. ## Cost and submission Details for the model bound to a matched exposed operation may provide `base_price_usd` and `price_unit` when available. Explain relevant estimated cost and output count before a paid run; a base price may not include every size or model-dependent option, so do not present it as a guaranteed final charge. Use `get_balance()` when the user asks about available funds or an account/balance issue needs investigation. It returns `balance.balance_usd` and `balance.balance_microdollars`. Use only the connected account’s existing balance or entitlement. Authenticate through this plugin’s OAuth connection flow, never by collecting credentials in chat. If balance or entitlement is insufficient, explain why the task cannot run and stop; do not initiate or link to purchases, top-ups, subscriptions or upgrades. Execute only the run or batch the user has authorized. If this exact paid scope and budget were already appro
Preview of the first 4,000 characters. Read full instructions →
Release notes
Adds three focused image-generation skills, multilingual discovery keywords, explicit reference-input requirements, approved-job cost handling, and request-bound original output links. Updates review cases with the verified Model API tool names. Skills, MCP configuration and assets are unchanged from 1.0.4.
Declared in the saved package. Remote tools may change independently.
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package author
- RunComfy
- Keywords
- See keywords
- Review scenarios
- 5 positive · 3 negativeScenario counts, not test results.
Declared capabilities
- Generate images from text
- Create images from references
- Create character and scene variations
- Check generation status
Package observed Nov 18, 2026.
Technical details
- First seen
- Nov 18, 2026 · 06:00 UTC
- Last seen
- Nov 18, 2026 · 06:00 UTC
- Collection status
- Collected
plugin_asdk_app_6aec1d361bf08191a1061e69025ff4b1
Download plugin data (JSON)Plugin details: freshly prepared. Prepared . Refreshed when plugin data changes or after 6 hours. Your account and Follow status are live.