Type a scene. Watch Hermes draw it.
Prose becomes a six-frame film storyboard, stroke by stroke, in your browser. Kimi K2.5 reviews the board for film grammar, and Hermes learns how you direct — so the next scene already follows your rules.
Generate your own scene
Live API · free for the first scene · runs locally if API is asleep.
Up to 2000 characters. Kimi K2.5 parses, enriches, critiques, and extracts memory. The local SVG renderer draws.
Your storyboard will appear here.
~10 seconds end-to-end · six frames stagger in
◆ Kimi K2.5 review
★ Hermes saved a director rule
✎ Direct one frame
Click any frame above to select it, then describe the change. Hermes re-renders only that frame and learns your preference.
◐ Compose with Hermes
Or refine the whole scene in plain language. Hermes will re-render all six frames with your direction.
SVG, PNG, scene JSON, character bible, production packet — shotlist, camera notes, dialogue, continuity. The GIF replays the board fill-in for X/Discord posts.
// click a tab to inspect the underlying agent artifact
Every artifact you see is also written to disk by the
Hermes skill — these are the same files you'd find in
~/.hermes/skills/creative/storyboard/ after a run.
Storyboards are the bridge between writing and seeing. Hermes makes that bridge live.
- 01 parse prose → Scene JSON six shots, lens/movement/eye-line, strict enum schema
- 02 critique rendered PNG → patch list multimodal vision, seven whitelisted fields, old_value matched
-
03
extract director memory
→
reusable rule
style-only, plot-leak filter, persisted to
director_memory.json
Every role is its own callable skill. Provider-agnostic via OpenRouter. Kimi is not a label here — it is load-bearing in parse, critique, and memory extraction. How it stays grounded →
Kimi reasons. Renderer draws. Hermes remembers.
Storyboard is a reusable, inspectable creative workflow — not a one-shot toy.
- 01 Kimi K2.5 in three roles — scene parser, multimodal critic, memory extractor. Each role is its own reusable skill, callable from any Hermes workflow.
-
02
Persistent artifacts on disk
—
director_memory.json,character_bible.json— survive between sessions and ship as plain JSON. No black box. - 03 Future scenes inherit your direction. One revision in scene 1 changes how scene 2 renders. That's the Hermes self-improving pattern, applied to film grammar.
-
04
Installable as a Hermes skill.
git cloneinto~/.hermes/skills/creative/storyboardand describe a scene to Hermes — the skill loads automatically from chat, with your own API key, on your own machine.
- ✓ Strict Scene JSON schema with enums
- ✓ Whitelisted SVG grammar — no
script, nohref - ✓ Patch-only critique — one of seven allowed fields
- ✓ Shot labels cross-checked — no hallucinated frames
- ✓ Director memory cannot add plot facts
- ✓ Every inferred detail tagged by source
Kimi proposes. Storyboard verifies. Hermes remembers only what is safe to reuse. See README →
- ▣Editable SVG
- ▣PNG render
- ▣Animated GIF
- ▣Scene JSON
- ▣Character bible
- ▣Director memory
- ▣Shotlist CSV
- ▣Camera notes
- ▣Dialogue sheet
- ▣Continuity sheet
├── board.svg
├── board.png
├── board.gif
├── scene.json # the parsed shot grammar
├── revisions.json # Kimi K2.5 critique
├── character_bible.json # silhouette continuity
├── director_memory.json # learned direction rules
└── packet/ # DP-ready handoff
├── shotlist.csv
├── camera_notes.md
├── dialogue.md
└── continuity.md
Recent generations
Sample boards · refreshed as people share their generations.
No public boards yet — be the first.
Tick "Share to public gallery" before you generate.
Hermes learns how you direct
Director memory is the difference between draws-on-demand and grows-with-you.
Most AI tools treat each prompt as independent. Storyboard persists your stylistic choices: revise one frame with a free-text note, and Hermes extracts a generalised rule via Kimi K2.5 and applies it to every future scene that matches.
-
1
You revise one frame
Click any shot, write a free-text note — "more Hitchcock", "darker shadow", "silhouette only".
-
2
Hermes saves a rule
Kimi K2.5 generalises the note into a tagged preference. Persisted to
director_memory.json— survives sessions. -
3
Next scene applies it
Future scenes that match the tags (suspense, stairwell, pursuit…) are rendered with the rule, automatically. No re-prompting.
{
"preference": "For suspense, danger, and reveal moments, prefer
low-angle framing with stronger cast shadows. When
showing a threat or unseen antagonist, render them as
a partial silhouette rather than a fully-lit figure.",
"applies_to": ["suspense", "reveal", "danger", "stairwell",
"killer entrance", "pursuit"],
"source_revision": {
"scene": "01",
"frame": "1F",
"note": "more Hitchcock — low angle, harder shadow, killer as silhouette"
}
}
This site is a showcase
The skill itself runs locally inside Hermes Agent on your machine.
hermes-story.art is a witness, not a service.
The real skill is a small Python package plus a SKILL.md manifest
that drops into ~/.hermes/skills/creative/storyboard
and is triggered naturally from Hermes chat — describe a
scene and Hermes loads the skill automatically. Three steps:
Install the skill
One git clone, one env var. The skill lives in the standard Hermes skills directory.
git clone \
https://github.com/Zhekinmaksim/storyboard \
~/.hermes/skills/creative/storyboard
export OPENROUTER_API_KEY=sk-or-...
Trigger from Hermes chat
Hermes auto-loads the skill at startup. Use it via natural chat — no command memorisation.
you draft a storyboard for a noir
alley discovery scene
hermes [activates /storyboard]
[streams six frames live]
[Kimi K2.5 reviews]
[exports production packet]
Or run standalone
Pure CLI works too. Same pipeline, viewer at
localhost:7777.
storyboard full --stream \
"A detective enters…"
storyboard memory --show
storyboard packet scene.json