LoRA Space Builder
huggingface/skills
Builds and publishes a Gradio demo on Hugging Face Spaces for a LoRA, with the pipeline, UI and settings chosen to match that LoRA's task and model card.
Add a new HuggingFace-supported VAE to the stage1 tokenizer pipeline.
Install Stage1 Add Vae
$ npx skills add End2End-Diffusion/diffusion-bench --skill stage1-add-vae -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install End2End-Diffusion/diffusion-bench stage1-add-vae --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/End2End-Diffusion/diffusion-bench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/stage1-add-vae .claude/skills/stage1-add-vae && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "stage1-add-vae" agent skill from https://github.com/End2End-Diffusion/diffusion-bench/tree/main/skills/stage1-add-vae into .claude/skills/stage1-add-vae/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage1-add-vae", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/End2End-Diffusion/diffusion-bench/tree/main/skills/stage1-add-vaeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add End2End-Diffusion/diffusion-bench --skill stage1-add-vae -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install End2End-Diffusion/diffusion-bench stage1-add-vae --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/End2End-Diffusion/diffusion-bench.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/stage1-add-vae .agents/skills/stage1-add-vae && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "stage1-add-vae" agent skill from https://github.com/End2End-Diffusion/diffusion-bench/tree/main/skills/stage1-add-vae into .agents/skills/stage1-add-vae/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage1-add-vae", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add End2End-Diffusion/diffusion-bench --skill stage1-add-vae -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install End2End-Diffusion/diffusion-bench stage1-add-vae --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/End2End-Diffusion/diffusion-bench.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/stage1-add-vae .cursor/skills/stage1-add-vae && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "stage1-add-vae" agent skill from https://github.com/End2End-Diffusion/diffusion-bench/tree/main/skills/stage1-add-vae into .cursor/skills/stage1-add-vae/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage1-add-vae", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/End2End-Diffusion/diffusion-bench.git --path skills/stage1-add-vae--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add End2End-Diffusion/diffusion-bench --skill stage1-add-vae -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install End2End-Diffusion/diffusion-bench stage1-add-vae --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/End2End-Diffusion/diffusion-bench.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/stage1-add-vae .gemini/skills/stage1-add-vae && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "stage1-add-vae" agent skill from https://github.com/End2End-Diffusion/diffusion-bench/tree/main/skills/stage1-add-vae into .gemini/skills/stage1-add-vae/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage1-add-vae", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install End2End-Diffusion/diffusion-bench stage1-add-vaeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add End2End-Diffusion/diffusion-bench --skill stage1-add-vae -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/End2End-Diffusion/diffusion-bench.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/stage1-add-vae .github/skills/stage1-add-vae && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "stage1-add-vae" agent skill from https://github.com/End2End-Diffusion/diffusion-bench/tree/main/skills/stage1-add-vae into .github/skills/stage1-add-vae/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage1-add-vae", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add End2End-Diffusion/diffusion-bench --skill stage1-add-vae -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install End2End-Diffusion/diffusion-bench stage1-add-vae --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/End2End-Diffusion/diffusion-bench.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/stage1-add-vae .opencode/skills/stage1-add-vae && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "stage1-add-vae" agent skill from https://github.com/End2End-Diffusion/diffusion-bench/tree/main/skills/stage1-add-vae into .opencode/skills/stage1-add-vae/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "stage1-add-vae", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
stage1-add-vae- GitHub stars
- 105
- Token cost
- ~1.1k tokens
- SKILL.md length
- 426 words
- Files
- 6 (incl. scripts, references)
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- None found
At a glance
Add a new HuggingFace-supported VAE to the stage1 tokenizer pipeline.
- Works in 6 steps: Investigate the VAE → Add VAEConfig entry → Custom class (only if needed) → …
- Integrating a new VAE model from diffusers
- SKILL.md covers Quick overview, Step 0: Investigate the VAE, Step 1: Add VAEConfig entry and Step 2: Custom class (only if…, plus 4 more sections
- Runs Python scripts from its folder; calls uv
What it does
Stage1 Add Vae is an agent skill from End2End-Diffusion/diffusion-bench. Add a new HuggingFace-supported VAE to the stage1 tokenizer pipeline. Use when integrating a new VAE model from diffusers, adding autoencoder support, or the user says "add vae", "new vae", "integrate vae", "add autoencoder", "support X VAE".
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `references/custom-classes.md`, `references/eval-config-template.yaml` and `references/normalization.md`).
It sits in AI & LLM Engineering, covering Diffusion and image models and Model hubs and datasets. It works with Hugging Face. The repository describes itself as: Towards Holistic evaluation of Generative Diffusion Transformers!
When your agent uses it
- Integrating a new VAE model from diffusers
- Adding autoencoder support
- The user says add vae
- Add autoencoder
Example prompts
- “add vae”
- “new vae”
- “integrate vae”
- “/stage1-add-vae”
Requirements
- Python 3
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- Investigate the VAE
- Add VAEConfig entry
- Custom class (only if needed)
- Create eval config
- Update job script + docs
- Verify with reconstruction test
What it can do on your machine
Read from SKILL.md and the folder at commit 4848f0c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Stage1 Add Vae loads about 1.1k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 426 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 426 words (~1,059 tokens).
“Adding a VAE touches these files (all in deterministic locations):”
- name
- stage1-add-vae
Files
SKILL.md and 5 other files (scripts, references) in skills/stage1-add-vae of End2End-Diffusion/diffusion-bench.
- SKILL.md
- references/custom-classes.md
- references/eval-config-template.yaml
- references/normalization.md
- scripts/investigate_vae.py
- scripts/test_reconstruction.py
Open the folder on GitHubat commit 4848f0c
Compare with similar skills
Stage1 Add Vae next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Stage1 Add Vae this skillEnd2End-Diffusion/diffusion-bench | 105 | — | ~1.1k | Automated safety check: Pass | None | |
| LoRA Space Builderhuggingface/skills | 11k | 2 repos | ~8.4k | Automated safety check: Pass | Apache-2.0 | |
| DiffusersVectorSpaceLab/AREX-Skill | 328 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Discover MLrand/cc-polymath | 181 | 1 repos | ~574 | Automated safety check: Pass | MIT | |
| Stable Diffusion Image Generationtaracodlabs/aiden | 849 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Modelsguaardvark/guaardvark | 251 | — | ~782 | Automated safety check: Pass | MIT |
Similar skills
- Official
Diffusers
VectorSpaceLab/AREX-Skill
A skill your agent uses for Hugging Face Diffusers tasks: pipeline inference, schedulers, adapters/loaders, training recipes, modular pipelines, conversion helpers, CLI checks, and repo maintenance.
Discover ML
rand/cc-polymath
Automatically discover machine learning and AI skills when working with machine learning, PyTorch, training, inference, RAG, embeddings, fine-tuning, LLM, DSPy, HuggingFace, or diffusion models.
Stable Diffusion Image Generation
taracodlabs/aiden
Generate images via Stable Diffusion (HuggingFace Diffusers, local/API)
Models
guaardvark/guaardvark
Add any Hugging Face image or video model, checkpoint or LoRA to Guaardvark from a URL, list what is installed, and download registry models on request.
Comfy CLI
sundial-org/awesome-openclaw-skills
Install, manage, and run ComfyUI instances. An agent skill from sundial-org/awesome-openclaw-skills.
More from End2End-Diffusion/diffusion-bench
Setup
End2End-Diffusion/diffusion-bench
Set up and verify the nanogen development environment. An agent skill from End2End-Diffusion/diffusion-bench.
Related
Works with
Categories
Questions about Stage1 Add Vae
What does Stage1 Add Vae do?
Add a new HuggingFace-supported VAE to the stage1 tokenizer pipeline. Stage1 Add Vae is an agent skill from End2End-Diffusion/diffusion-bench. Add a new HuggingFace-supported VAE to the stage1 tokenizer pipeline.
When should I use Stage1 Add Vae?
Stage1 Add Vae fits situations like: integrating a new VAE model from diffusers; adding autoencoder support; the user says add vae; add autoencoder.
How do I install Stage1 Add Vae in Claude Code?
Run `npx skills add End2End-Diffusion/diffusion-bench --skill stage1-add-vae -a claude-code`. Or copy the skill folder (skills/stage1-add-vae in End2End-Diffusion/diffusion-bench) into .claude/skills/stage1-add-vae in your project. Claude Code loads it when a task matches its description.
How do I install Stage1 Add Vae in Codex?
Run `npx skills add End2End-Diffusion/diffusion-bench --skill stage1-add-vae -a codex`. Or copy the skill folder (skills/stage1-add-vae in End2End-Diffusion/diffusion-bench) into .agents/skills/stage1-add-vae in your project. Codex loads it when a task matches its description.
Can I use Stage1 Add Vae in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add End2End-Diffusion/diffusion-bench --skill stage1-add-vae -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stage1-add-vae, .gemini/skills/stage1-add-vae, .github/skills/stage1-add-vae and .opencode/skills/stage1-add-vae in your project.
What does Stage1 Add Vae need to run?
Going by SKILL.md and its folder, Stage1 Add Vae needs Python for the scripts in its folder and the command-line tools its instructions call (uv). Our summary lists: Python 3.
Does Stage1 Add Vae access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Stage1 Add Vae safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Stage1 Add Vae use?
No licence was found for Stage1 Add Vae or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Stage1 Add Vae use?
About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.
What are the alternatives to Stage1 Add Vae?
Skills that share tags, products or a category with Stage1 Add Vae: LoRA Space Builder (huggingface/skills, 11k stars), Diffusers (VectorSpaceLab/AREX-Skill, 328 stars), Discover ML (rand/cc-polymath, 181 stars) and Stable Diffusion Image Generation (taracodlabs/aiden, 849 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Stage1 Add Vae?
End2End-Diffusion (a GitHub organization) maintains it in End2End-Diffusion/diffusion-bench, which has 105 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on July 1, 2026.
Source: End2End-Diffusion/diffusion-bench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.