deepbeepmeepdeepbeepmeep/Wan2GP/wangp-agent/SKILL.md

wangp-agent

Skill11k starsChanged 15 days agoLicence not identifiedView on GitHub

Use when an agent needs to operate WanGP: discover available model capabilities, choose a model, inspect accepted inputs and setting values, build settings, run generation through the MCP server or Python API, poll jobs, cancel jobs, and return generated media artifact paths.

Jun 5, 2025Hunyuan Video Avatar with only 10GB of VRAM, run this great models on most consumers GPU ! — Tencent-Hunyuan/HunyuanVideo-Avatar11 reactions · 5 comments
Apr 20, 2025Add Queues — lllyasviel/FramePack9 reactions · 11 comments
Jul 10, 2025WanGP 6.6: Low VRAM support for Vace Multitalk — MeiGen-AI/MultiTalk5 reactions · 5 comments
Jun 6, 2025[FR] Please support ref image and multiple control videos in Wan VACE — huggingface/diffusers5 reactions
Mar 2, 2025Wan2.1 GP: generate a 8s WAN 480P video (14B model non quantized) with only 12 GB of VRAM — Wan-Video/Wan2.14 reactions · 3 comments

26 more on GitHub

Jul 10, 2025WanGP supports of LTX Video and IC-lora — Lightricks/LTX-Video3 reactions · 2 comments
Feb 12, 2025Add support for APG (adaptive projected guidance) + unconditionnal SLG — leejet/stable-diffusion.cpp3 reactions · 3 comments
Oct 27, 2025WanGP Ovi Implementation: only 6GB of VRAM to generate in one minute and half 121 frames at 720p with audio / speeches — character-ai/Ovi2 reactions
Jun 11, 2025WanGP 5.5 : Low VRAM support for Hunyuan Custom Audio and Edit — Tencent-Hunyuan/HunyuanCustom2 reactions · 4 comments
Sep 14, 2026WanGP v13.0 issue — LykosAI/StabilityMatrix1 reaction
Apr 14, 2026Guard `torch.distributed` submodule imports for ROCm builds — deepbeepmeep/WanGP1 reaction · 2 comments
Oct 20, 2025Beware of Using Eddy Models — deepbeepmeep/WanGP1 reaction · 1 comment
Oct 2, 2025Why is VAE decoder hardcoded to CPU? Severe performance issue with sufficient GPU — deepbeepmeep/WanGP1 reaction · 6 comments
Sep 12, 2025ADD QUANTO MODELS SUPPORT — Comfy-Org/ComfyUI1 reaction · 1 comment
Aug 24, 2025Infinitetalk support in Wan2GP, fast and only needs 8 GB of VRAM to generate 81 frames at time — MeiGen-AI/InfiniteTalk1 reaction · 4 comments
Jul 10, 2025NAG is in WanGP 6.7 — ChenDarYen/Normalized-Attention-Guidance1 reaction
Jul 3, 2025--lora-dir should be a path to a directory that contains Loras — deepbeepmeep/WanGP1 reaction
Jun 7, 2025New audio-driven video generation model - Wan2GP — Comfy-Org/ComfyUI1 reaction
Sep 30, 2026fix: Avoid audio re-encoding for post-processing + preserve all tracks — deepbeepmeep/WanGP0 reactions
Sep 30, 2026feat: general Opus audio codec support — deepbeepmeep/WanGP0 reactions
Sep 23, 2026fix(ROCm): H3 Comfy Kitchen dispatch on ROCm — deepbeepmeep/WanGP0 reactions · 2 comments
Sep 17, 2026feat(video): add 16-bit FLAC audio codec for MP4 and MKV — deepbeepmeep/WanGP0 reactions
Sep 17, 2026feat: adds general FLAC support — deepbeepmeep/WanGP0 reactions · 1 comment
Sep 6, 2026Performance tweaks? — 6Morpheus6/wan2gp-amd0 reactions
Aug 13, 2026Add Wan2GP (WanGP) playbook — AI video generation on DGX Spark — NVIDIA/dgx-spark-playbooks0 reactions
Aug 5, 2026wan2go video gen gpu poor — gatrivi/catts0 reactions
May 8, 2026fix(mps): prevent Metal command buffer double-commit crash on 5B quanto models — deepbeepmeep/WanGP0 reactions · 2 comments
May 7, 2026fix(mps): 5 community-reported MPS startup + dependency fixes — deepbeepmeep/WanGP0 reactions
Sep 25, 2025[FEATURE] HTML-Based Queue with drag and drop reordering — Wan-Video/Wan2.10 reactions
Jul 2, 2025Alternative Skip Layer Guidance (SLG) node implementation — Comfy-Org/ComfyUI0 reactions
Mar 2, 2025Feat: Wan2GP Support — kijai/ComfyUI-WanVideoWrapper0 reactions

On YouTube · 10

Mar 9, 2026LTX Video 2.3 Without ComfyUI | WAN2GP One-Click Setup — Prompt Mastery55k views · 241 comments
Nov 4, 2025🎬 Create AI Videos for Free on Google Colab with Wan2GP | Step-by-Step Tutorial — Fuzz Puppy29k views · 81 comments
Jan 15, 2026Run LTX 2 + Wan2GP Locally (Minimal 8GB VRAM Setup Guide) — Prompt Mastery23k views · 61 comments
Dec 21, 2025Introduction to Wan2GP — noodlepop8.9k views · 1 comment
Nov 4, 2025Faster 4 Step 704p Video Generation Using Wan 2.2 TI2V 5B + FastWan Or Turbo | WanGP Tutorial — AxiomGraph8.3k views · 29 comments

5 more on YouTube

Oct 23, 2025Run AI Image & Video Generation Locally with WanGP | One-Click Setup + Performance Boost — CodingPaw8k views · 5 comments
Jul 23, 2026Run Wan2GP FREE on Google Colab | No GPU Required | Wan 2.2, FLUX & Qwen Image — AiThatSpeaks7.6k views · 34 comments
May 31, 2026LTX 2.3 + EditAnything with Reference Image in Wan2GP! — UnReal Jake7.5k views · 5 comments
Nov 3, 2025WanGP The EASY Portable Version! Forget Manual Installation — AxiomGraph5.5k views · 18 comments
Nov 3, 2026Run LTX 2.5 & MiniMax H3 on Any PC — No GPU Needed (Google Colab + WanGP) — Outlier Ideas484 views · 8 comments

On Bluesky · 1

Mar 5, 2025Alibaba's Wan2.1 GP Generates a 8s WAN 480P video (14B model non quantized) with only 12 GB of VRAM or reduced the VRAM consumption of… — @sungkim.bsky.social6 likes and reposts · 1 reply

On the web · 1

Sep 7, 2025Deepbeepmeep Wan2gp | MAGI//ARCHIVE — tom-doerr.github.io

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 1 is distinctive, and 9 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free