repo·evals
· ·main@HEAD

Pixelle-Video

AIDC-AI/Pixelle-Video

🛠69 / 100
🎯

📝
🗺
01Signal scanning信号发现02Content acquisition内容获取03Content understanding内容理解04Topic curation选题决策05Content production内容生产06Creative assembly创意组装07Distribution & feedback分发反馈08Learning学习
📍video
🧬

🛑
0–29
⚠️
30–49
🛠
50–79
🏭
80–100
69
🛠· 69 / 100
  • 6 claims passed, no critical failures
  • MIT / Apache / etc., installable per deployment.install_methods
  • release_pipeline_score=3 + pushed in 90-day window
  • multilingual_readme=true
  • compound layer needs a logged scenario run

#1👤
#2🎯
#3🧭
#4

shortlongIdea (text prompt)想法 (文字 prompt)LLM decides:LLM 决定:script structure脚本结构Short narrative短叙事(30-60s)(30-60 秒)Long-form长格式(60-90s)(60-90 秒)LLM decides:LLM 决定:scene composition场景组成Voiceover gen配音生成(TTS / cloned voice)(TTS / 克隆音)Scene + audio场景 + 音频+ music assembly+ 音乐组装Finished MP4成品 MP4

docker-compose upany (Docker)easy
Windows installer (binary)Windowseasy
  • 🌐
LLM provider (OpenAI / Anthropic / local — pick via llm_presets)
Script + scene + voiceover decision-making
BYOK; per-video cost depends on choice + complexity
Asset / video gen provider (configurable)
Scene visuals + voiceover audio
Per-asset cost
· 7
6 1
+40
+14
+12
+6
-3
0

6 / 7
passed claim-001

passed claim-002

passed claim-003

passed claim-004

passed claim-005

untested claim-006

input_contract
output_contract
determinism
idempotence
no_skill_callouts
failure_mode_clarity

workflow_correctness
declared_call_graph
stop_conditions
handoff_points
atom_evidence
error_propagation
partial_failure_handling

goal_achievement
direction_judgment
quality_judgment
meaningful_autonomy
handoff_timing
observed_call_graph
failure_recovery

  • core user-facing layer untested → capped at 'usable'
  • hybrid-repo rule: archetype 'orchestrator' requires end-to-end evaluation of the user-facing layer
  • evidence_completeness='partial' (not portable) → capped at 'usable'

  • only 2/3 critical claims covered

archetype: orchestratorcore_layer_tested? Falseevidence: partialrecommended: usablefinal: usable
ceiling 1 · core user-facing layer untested → capped at 'usable'
ceiling 2 · hybrid-repo rule: archetype 'orchestrator' requires end-to-end evaluation of the user-facing layer
ceiling 3 · evidence_completeness='partial' (not portable) → capped at 'usable'

claim-001Python pipeline + FastAPI backend for fully-automated short-video generationcriticalpipeline-implementation● passed
claim-002Docker + Windows package distributionhighdistribution● passed
claim-003Apache 2.0 LICENSE + NOTICE presentcriticallicensing● passed
claim-004Substantive documentation (mkdocs site + per-area docs/)highdocumentation● passed
claim-005LLM provider abstraction (multi-provider support)highprovider-abstraction● passed
claim-006Live e2e — generate one short video from idea to finished MP4criticalend-to-end○ untested
claim-007Bilingual README (EN + 中文)mediumdocs-i18n● passed

0%
0.00s
0