Create beautiful visual art in .png and .pdf documents using design philosophy.Kurmak için tıkla
Skill- OpenClaw
image-with-comfyui
Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like "make a picture of", "…
“3D, modelleme ve görsel” alanında bir skill. OpenClaw için hazır komut var.
Tüm açıklama
Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like "make a picture of", "replace the background", "cut out / extract the subject of", "turn this into a video", "edit my photo", or "make a 3D mesh of this character". Not for simple non-generation image tweaks. **Qwen-Image 2.1 Turbo** (model id `qwen21t`, the fast 8-step default) is the default model for both text-to-image (T2I) and image editing/multi-image (I2I); it can also **cut out / extract the main subject or any image element into a transparent-background image**. The earlier default **Qwen-Image 2.1** (id `qwen21`, 25-step) is still available via `--model qwen21`. Z-Image / SD3.5 (T2I), Qwen Image Edit (2511, single-image), **MiniMax H3 (FastH3 v2)** (I2V `h3_i2v` default / T2V `h3_t2v` — FastH3 v2 now generates video with an audio track, adding audio-enabled video generation to this skill), Wan2.2 (I2V), and **Pixal3D / Trellis2 (I2M, default image → 3D GLB mesh)** are available. The older **Hunyuan 3D v2.1 (I2M)** is still available under the `hyi2m` entry point. **Destructive cleanup disclosure:** after a run completes and results are saved locally, the script **deletes the server-side copies on the ComfyUI server of the generated outputs of this run AND of any input materials uploaded for generation** (source images / reference images) via `POST /purge_after_retrieval`, unless the user opts out via `--keep` or `COMFYUI_PURGE=0`. This removes only the generated outputs of the current run and the input materials uploaded for that run — nothing else on the server. The agent should tell the user before running when it will delete server-side copies, including any source/reference materials still needed, and honor `--keep` if the user wants to retain them. **All-or-nothing:** the script deletes server copies only when *every* required output of this run has been safely downloaded and saved locally; if **any** output fails to retrieve, nothing is deleted on the server — the run leaves the results available on the server for retry. Purge attempts are retried on every run (a persistent disable after repeated failures was intentionally removed)
- Skill
- 3D, modelleme ve görsel
Kur
Programını seç, komut kendini yazsın.
clawhub install @sunshinejnjn/image-with-comfyui --version 4.7.5ClawHub CLI gerekir: npm install -g clawhub
Komutlar yayıncının kayıt bilgisinden üretildi; ANG skills bunları çalıştırıp denetlemedi.
Basitçe
Teknik bilgi gerekmez.
- Nedir?
- Skill, ajanına (Claude Code, Codex gibi) yüklenen bir talimat paketidir. Telefona uygulama yüklemeye benzer: bir kez kurarsın, ajan o işi nasıl yapacağını bilir.
- Ne işe yarar?
- “3D, modelleme ve görsel” işlerinde kullanılır. Yayıncının sözleriyle: Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like "make a picture of", "replace the backgrou…
- Örnek istek
- “Bu fikir için bir görsel taslak hazırla.”
- Ajanlar
- OpenClaw için hazır komut var.
- Güvenilir mi?
- Yıldız bilgisi yok · lisans belirtilmemiş. Kurmadan önce kaynağa bak.
Benchmark
Hangi ajanda ne kadar güçlü?
Benzerleri
3D, modelleme ve görsel alanından.
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as ph…Kurmak için tıkla
SkillDeploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and pr…Kurmak için tıkla
SkillCreate, inspect, validate, and save editable 3D building scenes with Pascal's MCP server.Kurmak için tıkla
MCPKurmaya hazır mısın?Kur