AGENT SKILL

generation

Guides Zero123Plus single-image to multi-view generation, ControlNet variants, model choices, camera outputs, and postprocessing workflows.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
generation
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Guides Zero123Plus single-image to multi-view generation, ControlNet variants, model choices, camera outputs, and postprocessing workflows.
disable-model-invocation
true

02 资源文件 8

03 SKILL.md 正文

Zero123Plus Generation

Use this sub-skill when the task is about producing, adapting, or debugging Zero123Plus multiview outputs from a single image: base v1.1/v1.2 runs, depth ControlNet, normal ControlNet, six-view grid interpretation, matting postprocess, or reference-only upstream image synthesis for inputs.

Do not use this sub-skill for serving or deployment surfaces such as Streamlit, Gradio, Docker/Gitpod, or Cog. Route those questions to ../deployment/SKILL.md instead.

Read first

Bundled scripts

Routing procedure

  1. Identify the requested flow: base multiview generation, depth ControlNet, normal ControlNet, postprocess-only work, or optional image synthesis before Zero123Plus.
  2. Check GPU and cache readiness before a real run. The bundled scripts default to local-cache-only loading; pass --allow-download only when network access and model fetches are approved.
  3. For a standard six-view grid, use the bundled script that matches the requested model family. The scripts already encode the source defaults for scheduler choice, width, height, and output layout.
  4. For camera layout, view ordering, and license questions, use the model-and-camera reference. For exact callable signatures and preprocessing details, use the API reference.
  5. If the user asks about Streamlit, Gradio, Docker, or Cog rather than the core generation path, switch to the deployment sub-skill instead of duplicating those details here.

Stop conditions

  • No CUDA GPU is available for a real generation run.
  • The requested model or custom pipeline is not already cached and downloads are not approved.
  • The user is asking about training or finetuning, which this repository does not expose.
  • The issue is really about serving or deployment rather than generation.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351