Higgsfield Comic To Video

Higgsfield Comic-to-Video Skill

What this skill does

Animates a user-supplied comic panel, manga page, webtoon strip, or sequential art illustration into video. The skill reads the panel, infers narrative flow, and generates motion that respects reading order, art-style conventions, and dialogue timing.

A source image (the comic panel or page) is always required. This skill is a mandatory image-to-video (I2V) skill — it cannot run without a start image. Before any generation call can happen, the user must provide the panel file and the higgsfield:media_upload → higgsfield:media_confirm flow must complete successfully.

Model routing

Primary and fallback video models

Routing rule: Use wan2_6 by default. Fall back to seedance_2_0 when: (1) wan2_6 is unavailable, (2) the user wants duration outside [5, 10, 15], (3) the user wants genre tone control, or (4) the user wants audio/end_image roles. Never switch silently — state what changes.

MODEL-06 directive: If a parameter is rejected at generation time, call higgsfield:models_explore with the target model name. Full parameter tables: references/model-specs.md.

Per-platform aspect ratio and duration

Quick rule: 9:16 for TikTok / Reels / Shorts, 16:9 for YouTube, 1:1 for Instagram feed. Full per-platform table: references/model-specs.md.

Prompt-building workflow

1. Gather intent — Confirm with the user: reading order (Western LTR / Manga RTL / Webtoon Vertical / etc.), source art style, target platform, aspect ratio, and duration.

2. Select model — Apply the routing table above. wan2_6 by default.

3. Build the prompt — Use the craft principles in the references below:

   • 2-second hook technique from references/hooks.md
   • Reading order, art-style preservation, dialogue handling, panel-to-motion techniques from references/panel-craft.md
   • Worked example prompts by comic format from references/examples.md

4. Present for review — Show the assembled prompt and all parameters to the user for review and refinement before any upload or generation call.

Opt-in generation

Generation costs Higgsfield credits and requires explicit user confirmation. This skill never auto-generates.

Full step-by-step flow (confirmation gate, balance/cost surface, generate → poll → display): ../../shared/generation-flow.md

This skill's primary model: wan2_6

Media upload — MANDATORY (not conditional)

This skill always requires a source image. The media branch is not conditional — it always runs before generation. Do not skip it.

Required sequence:

1. Ask the user to provide the comic panel or page file (PNG, JPG, or WebP).
2. Call higgsfield:media_upload with the file → receives a pending_id.
3. Call higgsfield:media_confirm with the pending_id → receives a confirmed_id.
4. Attach the confirmed_id to the input_files array with role image before calling higgsfield:generate_video.

input_files: [{ "id": "<confirmed_id>", "role": "image" }]

Never pass a pending_id directly to input_files. Never attempt generation without first completing the upload pair. A missing or unconfirmed image will cause wan2_6 to reject the request.

See ../../shared/generation-flow.md Step 2b for the atomic-pair detail and full input_files structure.

Tool signatures: ../../shared/mcp-tools.md

Reference materials