Higgsfield Faceless Video
Higgsfield AIOfficialPublished by Higgsfield AI
- Skill
- Content generator
- Design and creative
- MIT
- Low risk
- Has scripts
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The higgsfield-faceless-video skill provides a structured process for creating finished faceless video content. It supports various formats such as illustrated explainers, documentaries, illustrated stories, and children's music videos. The skill manages the end-to-end production workflow, including script validation, voice selection, asset management, and final assembly of video and audio blocks. It also provides capabilities for editing previously generated videos and adding subtitles.
What it does
- Generates finished faceless videos based on user-provided topics and scripts.
- Supports multiple production modes including illustrated explainers, channel-style motion, and children's songs.
- Validates scripts against duration requirements and timing gates before generation.
- Manages voice selection and dialogue generation using specified presets.
- Assembles video and audio blocks into a final output file.
- Adds subtitles to videos using local transcription models.
When to use it
- When you need to create a narrated explainer or documentary video.
- When you want to produce a children's song video with consistent visuals.
- When you need to edit or update a previously generated faceless video.
- When you require a video with a specific visual style and structured narration.
Advantages
- Ensures consistent visual identity across video blocks.
- Provides tools to verify script timing and narration duration before incurring costs.
- Supports specific production modes for different content types like diagrams or stories.
- Enables precise assembly of video and audio pairs without altering speech speed.
Usage examples
- “make a faceless video about the history of the steam engine”
- The agent will initiate the production workflow to create a documentary-style video, including script validation and asset generation.
- “make a children's song video about counting apples”
- The agent will use the song production mode to generate a synchronized music video based on the provided topic.
- “edit this faceless video to change the narration in the second block”
- The agent will use the editing workflow to update the specified block while preserving the rest of the video's production state.
- “create a narrated explainer about photosynthesis”
- The agent will generate an illustrated explainer video using diagram-led scenes and narration.
Install
Download the skill as a ZIP:
https://autogineer.com/agent-skills/higgsfield-ai/higgsfield-faceless-video/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip higgsfield-faceless-video.zip -d .agents/skills
Documentation by Higgsfield AI
Faceless video
Create one finished video with a consistent visual style and narration. For an illustrated explainer use deliberate, diagram-led scenes; for a story or documentary adapt the pacing and visuals to the brief. Do not treat an explainer as a request for rapid cuts. Preserve choices and assets supplied by the user.
Choose the requested mode before generating: illustrated explainers use references/production.md; fast-cut channel motion uses references/channel-motion.md; stills and picture stories use references/picture-story.md; a sung children's music video uses references/song.md; explicitly requested talking characters use references/talking-characters.md; a requested presenter overlay uses references/presenter.md alongside the motion workflow; edits to a previously generated video use references/editing.md. A request for background music alone is not a song request. Never infer a presenter from an incidental photo.
When the brief supplies animation_mode, treat fully_animated as motion and scene_based as stills without asking again. Resolve song intent from the complete brief, including topic and script; an explicitly sung children's video uses song mode even when a voice is supplied. Preserve the production mode when continuing or editing an existing video.
Before spending credits
Resolve missing topic, approximate duration, aspect ratio, language, visual style, voice, music and subtitle choices. Never invent a preset or voice ID. Use higgsfield preset list video-explainer --json and higgsfield voices list --json for current choices, and resolve a selected preset with higgsfield preset resolve video-explainer <id> --json. Confirm photo roles before using reference images. Honor the requested duration; never silently round it up.
Find this skill's installed directory and retain its absolute path as SKILL_DIR. Keep all work in a persistent session directory, not the skill directory. Before generation verify higgsfield account status, ffmpeg, ffprobe, python3, curl, and awk, and inspect the live schemas using higgsfield model get for each planned model. Estimate generation costs with higgsfield generate cost where supported; if an estimate is unavailable, disclose that before generation. If any required stage, model, dependency, or requested feature is unavailable, explain and stop before paid work. Do not call explainer_video or video_explainer.
Read references/production.md for the generation, assembly, QC, recovery and delivery procedure. For subtitles, read references/captions.md and check its dependencies before paid generation. Read references/creative.md for style, assets, long-form planning and review, references/styles.md for style guidance, and references/prompts.md when writing the scene plan. The executable helper scripts/assemble_blocks.sh assembles ordered video/audio pairs without changing speech speed; read its usage before running it. The previous skill name is supported for existing installations.
Files
- ATTRIBUTION.mdAdded by AutoGineer890 B
- LICENSELicence file added by AutoGineer1.0 KiB
- SKILL.md3.5 KiB
- references/captions.md1.3 KiB
- references/channel-motion.md3.8 KiB
- references/creative.md2.6 KiB
- references/editing.md1.3 KiB
- references/picture-story.md3.3 KiB
- references/presenter.md2.1 KiB
- references/production.md4.0 KiB
- references/prompts.md903 B
- references/song.md2.7 KiB
- references/styles.md1.9 KiB
- references/talking-characters.md1.7 KiB
- scripts/assemble_blocks.shScript15.1 KiB
- scripts/assemble_final.shScript24.6 KiB
- scripts/assemble_partial_edit.shScript10.7 KiB
- scripts/assemble_slides.shScript26.1 KiB
- scripts/audio_to_captions.pyScript26.2 KiB
- scripts/bind_scene_frame_results.pyScript6.3 KiB
- scripts/build_scene_timeline.pyScript9.3 KiB
- scripts/burn_captions.shScript3.8 KiB
- scripts/check_voice.shScript1.0 KiB
- scripts/measure_narration_takes.pyScript5.4 KiB
- scripts/presenter_composite.shScript8.4 KiB
- scripts/speech_metrics.shScript3.1 KiB
- scripts/tests/test_assembly.pyScript2.5 KiB
- scripts/tests/test_captions.pyScript953 B
- scripts/tests/test_channel.pyScript3.0 KiB
- scripts/tests/test_modes.pyScript7.8 KiB
- scripts/tests/test_song.pyScript1.1 KiB
- scripts/tests/test_timeline.pyScript2.5 KiB
- scripts/trim_static_head.shScript2.2 KiB
- scripts/validate_motion_script.pyScript33.5 KiB
- scripts/validate_song_prompt.pyScript8.6 KiB
scripts/presenter_composite.sh
#!/usr/bin/env bash
# Usage: presenter_composite.sh background.mp4 presenter.mp4 output.mp4 [--style cutout|badge|fullframe] [--pos br|bl|tr|tl]
set -euo pipefail
STYLE="cutout"; POS="br"; KEY="auto"; CUT_H_FRAC="0.64"; CUT_W_FRAC="0.72"
BADGE_FRAC="0.355"; BADGE_CROP_Y="40"; MARGIN_FRAC=""; DISC="0xE8DFD0"
ARGS=()
while [[ $# -gt 0 ]]; do
case "$1" in
--style) STYLE="$2"; shift 2 ;;
--pos) POS="$2"; shift 2 ;;
--key) KEY="$2"; shift 2 ;;
--cut-h-frac) CUT_H_FRAC="$2"; shift 2 ;;
--cut-w-frac) CUT_W_FRAC="$2"; shift 2 ;;
--badge-frac) BADGE_FRAC="$2"; shift 2 ;;
--badge-crop-y) BADGE_CROP_Y="$2"; shift 2 ;;
--margin-frac) MARGIN_FRAC="$2"; shift 2 ;;
--disc-color) DISC="$2"; shift 2 ;;
-h|--help) grep '^#' "$0" | sed 's/^# \{0,1\}//'; exit 0 ;;
*) ARGS+=("$1"); shift ;;
esac
done
[[ ${#ARGS[@]} -eq 3 ]] || { echo "usage: presenter_composite.sh BLOCK TALK OUT [--style cutout|badge] (see --help)" >&2; exit 2; }
BLOCK="${ARGS[0]}"; TALK="${ARGS[1]}"; OUT="${ARGS[2]}"
[[ "$STYLE" == "cutout" || "$STYLE" == "badge" || "$STYLE" == "fullframe" ]] || { echo "bad --style '$STYLE'" >&2; exit 2; }
[[ "$POS" == "br" || "$POS" == "bl" || "$POS" == "tr" || "$POS" == "tl" ]] || { echo "bad --pos '$POS' (br|bl|tr|tl)" >&2; exit 2; }
if [[ "$STYLE" == "cutout" && ( "$POS" == "tr" || "$POS" == "tl" ) ]]; then
echo "cutout is bottom-only (torso is cut at the frame edge) — use --pos br|bl or --style badge" >&2; exit 2
fi
for f in "$BLOCK" "$TALK"; do [[ -f "$f" ]] || { echo "missing input: $f" >&2; exit 2; }; done
probe() { ffprobe -v error -select_streams v:0 -show_entries stream="$2" -of csv=p=0 "$1"; }
BW=$(probe "$BLOCK" width); BH=$(probe "$BLOCK" height)
TW=$(probe "$TALK" width); TH=$(probe "$TALK" height)
CHROMA_CORE="format=gbrp,split[ks][km];[km]geq=r='255*gt(g(X,Y)*100,42*(r(X,Y)+g(X,Y)+b(X,Y)))*gt(g(X,Y),r(X,Y)+10)*gt(g(X,Y),b(X,Y)+10)':g='0':b='0',extractplanes=r,dilation,gblur=sigma=1.2,lutyuv=y=negval[ka];[ks][ka]alphamerge,despill=type=green"
CORE=""; ROUTE=""
if [[ "$KEY" == "auto" ]]; then
SAMPLES=$(for XY in "8:8" "iw-48:8" "8:ih/4" "iw-48:ih/4" "iw/2-20:8"; do
X="${XY%%:*}"; Y="${XY##*:}"
ffmpeg -v error -ss 1 -i "$TALK" -vf "crop=40:40:${X}:${Y},scale=1:1" -frames:v 1 -f rawvideo -pix_fmt rgb24 - 2>/dev/null | od -An -tu1 | awk '{print $1, $2, $3; exit}'
done)
read -r MR MG MB SIM <<<"$(echo "$SAMPLES" | awk '
{r[NR]=$1;g[NR]=$2;b[NR]=$3;sr+=$1;sg+=$2;sb+=$3;n++}
END{mr=sr/n;mg=sg/n;mb=sb/n;mx=0;
for(i=1;i<=n;i++){d=sqrt((r[i]-mr)^2+(g[i]-mg)^2+(b[i]-mb)^2)/441.67; if(d>mx)mx=d}
s=mx+0.04; if(s<0.08)s=0.08; if(s>0.15)s=0.15;
printf "%d %d %d %.3f", mr, mg, mb, s}')"
KEY=$(printf "0x%02X%02X%02X" "$MR" "$MG" "$MB")
if [[ "$MG" -lt 80 || "$MG" -le "$MR" || "$MG" -le "$MB" ]]; then
echo "presenter_composite: background ($MR,$MG,$MB) is not green — is the talk clip on a green screen?" >&2; exit 1
fi
SAT=$(( MG - (MR > MB ? MR : MB) ))
if [[ "$SAT" -ge 60 && "$MR" -lt 30 ]]; then
SIM=$(awk -v s="$SIM" 'BEGIN{print (s<0.11)?"0.110":s}') # chromakey needs a bit more reach on soft hair edges
CORE="chromakey=${KEY}:${SIM}:0.05,despill=type=green"; ROUTE="chromakey"
echo "KEY: $KEY -> chromakey=${KEY}:${SIM}:0.05"
else
CORE="$CHROMA_CORE"; ROUTE="chromaticity"
echo "KEY: $KEY (SAT=$SAT R=$MR) -> chromaticity key (g_norm>0.42)"
fi
else
CORE="chromakey=${KEY}:0.13:0.06,despill=type=green"; ROUTE="chromakey-manual"
echo "KEY: $KEY -> $CORE"
fi
run_qc() { # $1 = CORE filter chain, $2 = bg alpha max -> prints metrics; rc 0/1
local png rc temp_dir; temp_dir=$(mktemp -d) || return 1; png="$temp_dir/matte.png"
ffmpeg -y -v error -ss 2 -i "$TALK" -filter_complex "[0:v]$1" -frames:v 1 "$png" || { rmdir "$temp_dir"; return 1; }
QC=$(python3 - "$png" "$2" <<'PY'
import sys
from PIL import Image
import numpy as np
im = np.array(Image.open(sys.argv[1]).convert("RGBA"))
bgmax = float(sys.argv[2])
h, w = im.shape[:2]
a = im[:, :, 3].astype(int)
pts = [(8, 8), (w - 48, 8), (8, h // 4), (w - 48, h // 4), (w // 2 - 20, 8)]
bg = float(np.mean([a[y:y + 40, x:x + 40].mean() for (x, y) in pts]))
face = float(a[int(h * 0.30):int(h * 0.55), int(w * 0.40):int(w * 0.60)].mean())
torso = float(a[int(h * 0.60):int(h * 0.85), int(w * 0.35):int(w * 0.65)].mean())
ok = bg < bgmax and face > 245 and torso > 245
print(f"{'PASS' if ok else 'FAIL'} bg_alpha={bg:.0f} face_alpha={face:.0f} torso_alpha={torso:.0f}")
sys.exit(0 if ok else 1)
PY
); rc=$?
rm -f "$png"; rmdir "$temp_dir"; echo "$QC"; return $rc
}
FALLBACK=0
if QCRES=$(run_qc "$CORE" 16); then
echo "QC: $QCRES"
else
echo "QC: $QCRES"
BGV=$(sed -E 's/.*bg_alpha=([0-9]+).*/\1/' <<<"$QCRES")
if [[ "$ROUTE" == chromakey* && "$BGV" -lt 16 ]]; then
echo "QC: person alpha failed on chromakey with a clean bg -> auto-fallback to chromaticity key" >&2
CORE="$CHROMA_CORE"; ROUTE="chromaticity-fallback"; FALLBACK=1
if QCRES=$(run_qc "$CORE" 40); then
echo "QC(fallback): $QCRES"
else
echo "QC(fallback): $QCRES"
echo "presenter_composite: matte QC FAILED on both keys — regenerate this talking clip (bad green), do not tune thresholds" >&2; exit 3
fi
else
echo "presenter_composite: matte QC FAILED — regenerate this talking clip (bad green), do not tune thresholds" >&2; exit 3
fi
fi
even() { awk -v x="$1" 'BEGIN{ v=int(x+0.5); if (v%2) v=v+1; print v }'; }
VOICE="${OUT%.mp4}_voice.wav"
ACHAIN="loudnorm=I=-16:TP=-1.5:LRA=11,aformat=sample_rates=44100:channel_layouts=stereo"
if [[ "$STYLE" == "fullframe" ]]; then
FH=$(even "$BH")
FILTER="[1:v]${CORE},scale=-2:${FH}[p];[0:v][p]overlay=(W-w)/2:H-h:shortest=1[v];[1:a]${ACHAIN}[a]"
elif [[ "$STYLE" == "cutout" ]]; then
CH=$(even "$(awk -v h="$BH" -v f="$CUT_H_FRAC" 'BEGIN{print h*f}')")
CW_KEEP="$CUT_W_FRAC"
CW_OFF=$(awk -v f="$CUT_W_FRAC" 'BEGIN{printf "%.4f", (1-f)/2}')
case "$POS" in
br) OXY="x=W-w+6:y=H-h+2" ;;
bl) OXY="x=-6:y=H-h+2" ;;
esac
FILTER="[1:v]${CORE},crop=iw*${CW_KEEP}:ih:iw*${CW_OFF}:0,scale=-2:${CH}[p];[0:v][p]overlay=${OXY}:shortest=1[v];[1:a]${ACHAIN}[a]"
else
S=$(( TW < TH ? TW : TH ))
MAXY=$(( TH - S )); CY=$(( BADGE_CROP_Y > MAXY ? MAXY : BADGE_CROP_Y ))
CX=$(( (TW - S) / 2 ))
C=$(( S / 2 )); R=$(awk -v s="$S" 'BEGIN{print int(s*0.4375)}'); R2=$(( R * R ))
BMIN=$(( BW < BH ? BW : BH ))
BS=$(even "$(awk -v h="$BMIN" -v f="$BADGE_FRAC" 'BEGIN{print h*f}')")
px() { awk -v d="$1" -v f="$2" 'BEGIN{print int(d*f+0.5)}'; }
if [[ -n "$MARGIN_FRAC" ]]; then
MXL=$(px "$BH" "$MARGIN_FRAC"); MXR=$MXL; MYT=$MXL; MYB=$MXL
elif (( BW >= BH )); then # landscape: broadcast title-safe
MXL=$(px "$BW" 0.05); MXR=$MXL; MYT=$(px "$BH" 0.07); MYB=$MYT
else
MXL=$(px "$BW" 0.112); MYT=$(px "$BH" 0.131); MYB=$(px "$BH" 0.167)
if [[ "$POS" == "br" || "$POS" == "bl" ]]; then
MXR=$(px "$BW" 0.218) # clear of the bottom-right button rail
else
MXR=$(px "$BW" 0.112)
fi
fi
case "$POS" in
br) OXY="x=W-w-${MXR}:y=H-h-${MYB}" ;;
bl) OXY="x=${MXL}:y=H-h-${MYB}" ;;
tr) OXY="x=W-w-${MXR}:y=${MYT}" ;;
tl) OXY="x=${MXL}:y=${MYT}" ;;
esac
FILTER="color=c=white:s=${S}x${S},format=gray,geq=lum='if(lte((X-${C})*(X-${C})+(Y-${C})*(Y-${C}),${R2}),255,0)',split[circ][circ2];[1:v]${CORE},crop=${S}:${S}:${CX}:${CY},format=rgba,split[pkA][pkB];[pkA]alphaextract[pa];[pa][circ]blend=all_mode=multiply[clipmask];[pkB][clipmask]alphamerge[personclip];color=c=${DISC}:s=${S}x${S}[bg];[bg][circ2]alphamerge[disc];[disc][personclip]overlay,scale=${BS}:${BS}[badge];[0:v][badge]overlay=${OXY}:shortest=1[v];[1:a]${ACHAIN}[a]"
fi
ffmpeg -y -v error -i "$BLOCK" -i "$TALK" -filter_complex "$FILTER" \
-map "[v]" -map "[a]" -c:v libx264 -crf 18 -preset veryfast -pix_fmt yuv420p -c:a aac "$OUT"
ffmpeg -y -v error -i "$TALK" -vn -af "$ACHAIN" -c:a pcm_s16le "$VOICE"
BGA=$(sed -E 's/.*bg_alpha=([0-9]+).*/\1/' <<<"$QCRES")
FCA=$(sed -E 's/.*face_alpha=([0-9]+).*/\1/' <<<"$QCRES")
TSA=$(sed -E 's/.*torso_alpha=([0-9]+).*/\1/' <<<"$QCRES")
SIDECAR="${OUT}.qc.json"
printf '{"script":"presenter_composite.sh","result":"PASS","style":"%s","pos":"%s","key":"%s","route":"%s","fallback":%s,"bg_alpha":%s,"face_alpha":%s,"torso_alpha":%s,"block":"%s","talk":"%s","out":"%s","ts":"%s"}\n' \
"$STYLE" "$POS" "$KEY" "$ROUTE" "$FALLBACK" "$BGA" "$FCA" "$TSA" \
"$(basename "$BLOCK")" "$(basename "$TALK")" "$(basename "$OUT")" \
"$(date -u +%Y-%m-%dT%H:%M:%SZ)" > "$SIDECAR"
echo "OUT: $OUT"
echo "VOICE: $VOICE"
echo "QC-SIDECAR: $SIDECAR"
Requirements and compatibility
Written for: Claude Code
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Needs: Declares allowed tools, Claude Code frontmatter, Needs Python
Security
What our scanner noticed· Low risk
- Scripts that your agent may run
This skill includes scripts that your agent may run. Read them before you use it.
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Published by
- Higgsfield AI
- Publisher
- Higgsfield AI (Official)
- Source
- higgsfield-ai/skills · higgsfield-faceless-video · commit 2700040
- Licence
- MIT License (redistribution allowed)
- LICENSE (added by AutoGineer from LICENSE)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Higgsfield AI or Higgsfield AI.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download higgsfield-faceless-video.zip