modal-memory-image

Plugin modal-memory-image in bl1nk42/image-gen. Commands read from the repo's manifest — 1 month ago.

Skills (12)

• character-story-video

  Plan and produce a multi-part animated character story with stable identity, sequential scenes, reference images, image-to-video clips, audio planning, and continuity checks. Use for character stories, sequels, animated narratives, or multi-scene image/video sequences.

• dataset-curation

  Curate generated images into a clean training dataset, validate metadata, remove duplicates, and sync manifests/assets to Hugging Face.

• image-generation

  Production image generation through Modal + ComfyUI or configured providers. Use when creating, editing, analyzing, caching, queueing, or registering images, including text-bearing visuals, references, style consistency, and multi-image batches.

• meme-generator

  Create captioned memes from classic templates or a supplied background, with correct text encoding, line limits, preview, and export. Use for memes and social reaction images; do not use for original AI artwork.

• memory-recall

  Retrieve relevant project decisions, prior prompts, style preferences, debugging notes, and past outputs with source traceability. Use when the user asks what was decided, why a design exists, or wants to reuse a known style/workflow.

• modal-operations

  Deploy, inspect, warm, cache, and troubleshoot the Modal + ComfyUI image backend and Hugging Face storage.

• nothing-design

  Apply the Nothing-inspired monochrome industrial design system to interfaces, dashboards, image prompts, and generated visual references. Use only when the user explicitly requests Nothing style/design or invokes this skill.

• photo-restoration

  Restore blurry, damaged, faded, or vintage photos while preserving identity, pose, composition, clothing, and historical character. Use for restoration, deblur, denoise, color correction, facial recovery, and high-resolution enhancement.

• prompt-engineer

  Design, refactor, evaluate, and version prompts for image generation, image analysis, style learning, and structured agent tools. Use when outputs are inconsistent, prompts need optimization, or a new provider/model is introduced.

• style-learning

  Learn and improve reusable image styles from liked references, votes, prompts, embeddings, and recent generation outcomes.

• video-generator

  Plan and execute professional AI video projects including commercials, explainers, short films, social clips, and image-to-video sequences. Use when the user requests video, animation, clips, B-roll, narration, music, or final assembly.

• visual-production-router

  Route visual requests to image generation, restoration, Nothing design, memes, character stories, video production, prompt engineering, memory, or the exact Modal tools. Use when a request spans multiple visual modalities or the right workflow is unclear.

Slash commands (3)

• /modal-memory-image:image-status

  Show image cache statistics, backend health, and recent queue state

• /modal-memory-image:prepare-prompt

  Preview normalized prompt, style suffix, and negative prompt before generation

• /modal-memory-image:sync-dataset

  Validate the local image dataset manifest and sync it to Hugging Face after confirmation

Subagents (1)

• style-curator

  Reviews liked image references, votes, prompts, and analysis results to propose a reusable style update without changing user subject details.

Hooks (1)

• PostToolUse

  python3 ${CLAUDE_PLUGIN_ROOT}/scripts/audit_event.py

Similar plugins