name: sprite-gen version: 3.7.0 description: "Generates images and game sprites through GPT or Grok with guided provider choices, separate saved defaults, automatic cleanup and optional curation. Handles sprite requests, ordinary image generation/editing, typography logos (로고, 타이포그래피, 타이틀 글자, 타이틀 로고, wordmark, logo, title lettering: a title screen drawn with the title in it, its lettering lifted out transparent), standalone image-to-video clips (i2v, animate this still, 그록 영상, 이매진 비디오, 스틸 움직여줘, first/last frame, reference-to-video, 영상 이어붙이기, 영상 편집, extend/edit a clip), clips from a video MCP on the agent (ZCRE, 지크 MCP), chroma removal, animation atlases, video loops, 큐레이션뷰, image candidates, 팔레트 스왑, palette swap, recolor, engine exports, repeating backgrounds, projected shadows, talking face layers over body motions (말하는 얼굴, 입 맞추기, 얼굴 층, lip sync, face pack), motion/contact inspection and optional scene composition from existing assets." license: Apache-2.0 depends_on: required_bins: - name: codex why: "gen --provider codex (image_gen via ChatGPT OAuth)" - name: ffmpeg why: "video-frames (clip -> frames) and video-set" - name: img2webp why: "video-loop WebP with exact alpha (libwebp); Pillow's animated writer drops -exact" - name: node why: "face-bake: the face pack's player (sprite-gen-face-v1.mjs) picks the frames" - name: rife-ncnn-vulkan why: "video-loop jump repair and video-cycle-align (RIFE v4.6 in-betweens with the -x -z test-time augmentation, release 20221029). Install once with sprite-gen rife install (sha256-checked, into the user data directory); SPRITE_GEN_RIFE or PATH override it; Linux without a GPU also needs libvulkan1 mesa-vulkan-drivers. Without it, walk and run loops are cut as filmed with a warning. SPRITE_GEN_RIFE_BACKEND=torch runs the same model in PyTorch instead, for a GPU with no Vulkan (pip install \"sprite-gen[torch]\", then sprite-gen rife install --backend torch; SPRITE_GEN_RIFE_DEVICE=cuda or cpu; SPRITE_GEN_RIFE_EXECUTOR=module:attr sends its frames to a GPU elsewhere, rife_torch.serve there)" required_scripts: - scripts/prepare_sprite_run.py - scripts/generate_sprite_image.py - scripts/gen_set.py - scripts/generate_sprite_video.py - scripts/video_canvas.py - scripts/video_frames.py - scripts/video_loop.py - scripts/video_set.py - scripts/extract_sprite_row_frames.py - scripts/interpolate_frames.py - scripts/compose_sprite_atlas.py - scripts/preview_animation.py - scripts/compose_selected_cycle.py - scripts/compose_sprite_gif.py - scripts/inspect_sprite_run.py - scripts/score_sprite_run.py - scripts/run_correction_loop.py - scripts/curation.py - scripts/serve_curation.py - scripts/slice_sheet_cells.py - scripts/unpack_atlas_run.py - scripts/export_curated_pngs.py - scripts/recolor.py modes: default: component-row

Sprite Gen

Generation entry points: make sprites, make an image, or animate a still into a video. Existing generation, extraction and export tools do the work; the user chooses the result and provider. For repeat a background, project a shadow, inspect motion or compose a scene, use the independent routes below directly with existing assets.

Start every generation request here

For a standalone video clip, read video and use sprite-gen video. This route works from any agent engine and delivers a verified MP4 plus report. For sprites or ordinary images, use the guides below.

Read user-workflow, then run the appropriate read-only guide:

$SPRITE_GEN_ROOT/.venv/bin/sprite-gen workflow --kind sprite
$SPRITE_GEN_ROOT/.venv/bin/sprite-gen workflow --kind image

When codex cannot run — exit 75

A call that names no provider (gen, logo, gen-set, video-set's mid-step redraw) runs on codex. When codex cannot run here — not signed in, or the codex usage of the account used up — and the user's choice for that is to ask (the default), the command generates nothing, prints one stderr line starting sprite-gen ask codex-unavailable: followed by JSON, and ends with exit 75. That is a question for the user, not a failure: never answer it yourself, never retry without the answer, never switch provider on your own.

Ask it in these words, with the reason from the line's cause (login: "로그인이 없어요", usage-limit: "사용량을 다 썼어요"):

지피티(codex)를 지금 쓸 수 없어요 — {이유}. 어떻게 할까요?

1. OpenAI API 로 만들기 (호출당 과금)
2. 그록으로 만들기
3. 멈추기

Side-view facing

Keep the side still, canvas placement and motion prompt facing the same direction. video-set observes each side input once before canvas placement and uses the requested --facing for both the canvas and clip prompt. Observation is record-only by default; it never changes the requested direction. Image correction requires explicit opt-in.

Direction is requested through the generation and motion prompts, which cannot guarantee model compliance. The detector can be wrong even at high confidence: review the still before choosing mirror or regen. Generation reports record direction, model, requested direction, model-reported confidence and correction under extra.facing; video reports and batch items use facing. final_direction is an observation or a value derived from it, not independent verification; final_direction_source identifies which. An uncertain or failed inspection records unknown and its reason and continues without correction; front-facing observations also remain unchanged. Mirroring does not preserve left/right accessory handedness.

Execution routes

Say a thing once: what an option says, leave out of the prompt. --direction, --facing, --handed, the key background and video --direction side each add their own sentence after your text, in one place. Your prompt carries the subject, its design and its pose. Text that says the opposite of an option ("facing left" with --facing right, the item on the other wrist) is sent as written with a warning (extra.prompt_notes, video-prompt's warnings): fix the prompt, do not send it — prompt-assembly.

Use existing automatic pipeline stages for background removal, extraction, alignment and export. Do not ask users to select each script. For a direct utility request, run that utility; no unrelated generation questions are needed. Preserve the row pipeline and component extraction for image sprites. One-shot grid generation and fixed cell cutting are not an alternative sprite-generation route.

For attack repeat coverage, observed one-shot returns and structured loop failure reports, follow video-pipeline.

A pinned idle or attack whose last frame the video model drew again has its wrap blended by default (video-loop --wrap-blend auto, a redraw only; off cuts as filmed), with details in loop repair.

Scene creation consumes finished assets and remains optional. Asset metadata owns frames, native durations and anchors; scene specs own placement, scale, playback rate, planes, camera and light. Measure stride only with declared same-foot contact and an isolated foot ROI; unknown contact stays unverified. Apply only a verified report for the exact selected asset with an explicit scene direction. Never infer walking direction from the bottommost silhouette, reverse frames or change source assets to make a scene work.

실행 인터프리터

SPRITE_GEN_ROOT is the absolute installed repository path. Use $SPRITE_GEN_ROOT/.venv/bin/sprite-gen or $SPRITE_GEN_ROOT/.venv/bin/python; do not assume an activated shell. 폴백 금지: create a missing venv or report the failure, never use an arbitrary global Python. NumPy 가 없는 인터프리터 fails at package import. Setup and diagnosis: interpreter.

RIFE for walk and run loops

Without RIFE, tell the user which loops went unrepaired and offer the install; after it, cut those loops again and run video-cycle-align. loop-repair.

Contracts and advanced tools

run-contract owns numeric requests, run layout, atomic publication and curated exports. architecture explains domain ownership. docs index lists every specialized feature and QA procedure. sprite-gen --help derives the command map from the package catalog. Never replace an engine stage — extraction, the loop cut, set alignment, loop repair — with a script of your own while presenting the result as a pipeline output. Where a stage's result is wrong, use the engine's own options first, keep the engine's result as the comparison, report the defect against the engine, and name in the delivery each stage done by hand and why. A new clip is for what no stage can reach: the drawing, the motion itself, a clip that holds no whole cycle (loop-review) — and a clip the engine names for one: when the alignment report's retake lists a loop (reason held-drawings: the cycle cut from its clip shows each drawing for two or three frames, the set's length leaves it at under 13 drawings a second, and frames between its drawings could not be made, so the loop halts there; or filmed-ghost: a filmed ghost frame has filmed ghosts on both sides, so no clean frame stands there and the loop shows it — reasons lists both where both apply), run the engine verbs first as above, then film that direction again and align the set anew rather than hand-painting the gap; tell the user what the reason was and that a new take usually fixes it (loop-repair section 4).

English · 한국어 · 日本語 · 简体中文 · Español · Français

Ask an image model for a "sprite sheet" and you know what you get: a character whose face changes every frame, a background that won't key out, poses that overlap and drift off-grid, and a PNG your game engine can't actually consume. Cute demo, useless asset.

sprite-gen is a Codex/Claude skill and a Python CLI that closes that gap. Give it one base image — it drives generation row by row, locks the character's identity, strips the chroma background to real alpha, extracts each pose as a clean transparent frame, and bakes a runtime atlas with a machine-readable manifest.json.frame_layout. Or hand the same still to a video model and get back a seamless, transparent loop per motion state. For the last 10% that generation never gets right, a curation webview lets you compare, reject, nudge and watch the loop live before you bake.

For side sprites, video-set uses --facing right|left consistently across canvas placement and clip prompts. Its direction detector is record-only by default (--facing-fix none) and can be wrong even at high confidence. Use gen --ref image.png --facing right to request orientation in the generation prompt; gen otherwise preserves orientation. Prompts request direction but cannot guarantee the result. Correction is opt-in: --facing-fix mirror, or gen --facing-fix regen; review the still before using either. See facing options.

Start with a request

Ask for sprites or an image. The agent checks access, asks only for missing provider/motion choices, runs the existing pipeline, and delivers the files. The curation view is optional. Save your choices once to reuse separate sprite and image defaults; a one-off request does not overwrite them. User workflow and defaults.

Pipelines, independent tools and scenes

The two sprite pipelines are ordered generation flows. Tool groups contain independent commands; scene creation is an optional workflow that consumes finished assets. sprite-gen --help prints this map and groups commands by the code domain that owns them.

flowchart LR
    subgraph A["A · atlas rows"]
        direction LR
        a1[prepare] --> a2["gen · gen-set"] --> a3[extract] --> a5[compose-atlas]
        a5 -.-> a4["curation (optional)"]
        a4 --> a5
    end
    subgraph B["B · video → loop"]
        direction LR
        b1[video-canvas] --> b2[video] --> b3[video-frames] --> b4[video-loop]
    end
    subgraph C["C · utilities"]
        direction LR
        c1[cutout] ~~~ c2[slice-sheet] ~~~ c4[ui-kit] ~~~ c3[unpack-atlas]
    end
    subgraph D["D · post-processing"]
        direction LR
        d1[recolor] ~~~ d2[export-*]
    end
    subgraph E["E · asset tools (independent)"]
        e1[background-tile] ~~~ e2[shadow] ~~~ e3[inspect-motion]
    end
    subgraph S["S · scene (optional)"]
        s1["existing assets + scene.json"] --> s2[scene-render]
        s1 --> s3[scene-inspect]
    end

Full index: docs/README.md. Architecture with domain and pipeline diagrams: docs/architecture.md.

What you actually get

• A transparent sprite atlas (sprite-sheet-alpha.png) — real alpha, no leftover chroma fringe, verified against white backgrounds (why the extractor unmixes instead of peeling).
• A runtime manifest (manifest.json.frame_layout) — absolute frame rectangles, per-state fps and loop flags. Your engine samples rectangles; it never guesses a grid.
• Breathe — a still idle becomes a living loop, deterministic squash & stretch baked on your curated frames from one sidecar field, anatomy-aware and pixel-true (details).
• Pixel-art that stays on grid — the Backbone Lattice measures one grid for the whole subject and holds every cut to it (details).
• Motion loops from video — jumps get a tall canvas, attacks a wide one, the loop point is the clip's own period, and a one-shot action is cut rest → action → rest. Walk cycles count foot crossovers into a clean two-step loop with smoothed seams (details).
• Deterministic colourways — recolor bakes N variant sheets from a palette map; same input, same output bytes (details).
• QA you can watch — per-state GIFs and contact sheets, so motion is judged as motion before anything ships. Cyclic locomotion (walk/run) stays experimental unless motion QA actually passes.
• Independent asset tools — build repeating backgrounds, project shadows from a foot anchor, and inspect timing, duplicate poses and contact evidence. Ambiguous feet produce an unverified measurement (details).
• Optional scene creation — place existing PNGs, external frame sequences, loop strips or runtime atlases on named planes, with camera motion and shared shadow projection. Sprite generation can finish before this step (details).

Quickstart

# install (Pillow, NumPy) into a fresh virtualenv — the venv is the only supported interpreter
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
sprite-gen --help

A · atlas rows — one still to a runtime atlas.

sprite-gen prepare --out-dir <run> --character-id <id> --base-image base.png   # request, guides, prompts
sprite-gen gen-set --run-dir <run> --provider codex                            # every state row, 4 at a time
sprite-gen extract --run-dir <run>                                             # chroma → transparent frames
sprite-gen compose-atlas --run-dir <run>                                       # sprite-sheet-alpha.png + manifest.json
sprite-gen curation --run-dir <run>                                            # (optional) pick, nudge, breathe

B · video → loop — one still to transparent loops (needs ffmpeg, img2webp, and your own grok login or XAI_API_KEY). Walk and run loops have their jump frames repaired and a direction set shares one cycle length through RIFE: install it once with sprite-gen rife install. Without it those loops are cut as filmed, with a warning (loop-repair).

sprite-gen video-set --base side=still.png --states idle,walk,run,jump,attack --out-dir set/
# per item: video-canvas → video → video-frames → video-loop; set/table.md names every result

Making clips through a video MCP connected to your agent? With ZCRE's (지크), the agent makes the clip on yo