Announcements

 

1-click Pinokio launcher for Captionz — batch image captioning with local Ollama vision models.

 

What it does

Installs and launches Captionz in one click:

 

Install — clones mikecastrodemaria/Captionz into app/, creates a venv and installs the requirements (Pillow, NiceGUI, Gradio). No PyTorch: the models run in Ollama, or in a bundled llama.cpp server (see below).

Start (web UI) — runs the NiceGUI interface (python app.py --ui web) and opens it.

Start (Gradio UI) — runs the Gradio interface (python gradio_app.py), the same one used on Hugging Face Spaces, here with the Ollama backend.

Update — resets the launcher and the app to their origin/main, refreshes deps.

Reset — removes app/ (and its venv) to reinstall from scratch.

Features (Captionz)

Vision-model detection · composed prompts (caption type × length × 20 checkable options × character name) or custom prompt with a live preview · sources: local path, upload, clipboard paste · image preview · editable captions · skip / overwrite / append policy · prefix / suffix (trigger word) · live status (model loading, timer, percent, ETA) · max-tokens cap and thinking switch · dark mode · CLI and benchmark script. See the app repo for full docs.

 

Requirements

Pinokio installed.

Either Ollama running on the machine (or reachable on the network: change the URL in the UI) with at least one vision model, for example ollama pull qwen3-vl:8b,

or no Ollama at all: pick the backend "llama.cpp (sans Ollama)" in the UI. On first captioning Captionz downloads a prebuilt llama-server for your machine (CUDA / Vulkan / CPU / Metal, 150–500 MB) and the default model Qwen2.5-VL-3B-Instruct Q4_K_M (~2.9 GB) into app/llamacpp/. Other GGUF models can be downloaded from Hugging Face or imported from a local Ollama store from the "Modèles llama.cpp…" dialog.

Captions are written next to each image as image.txt.

 

How to use

Install, then Start (web UI) and click Open Web UI.

Pick the vision model, add a folder path (or upload / paste images).

Choose a caption type, length and options; check the final prompt preview.

Click Captionner tout. Edit any caption in the right panel and save.

API

Captionz has no HTTP API of its own. Two programmatic entry points exist in app/:

 

Command line (Python, inside the launcher venv)

python cli.py ./dataset --recursive --type "Booru tag list" --length short

python cli.py ./dataset --model qwen3-vl:8b --option 3 --option 15 --prefix "mystyle, "

python cli.py --list-models

python cli.py --list-options

Python (import the core)

import sys; sys.path.insert(0, "app")

from pathlib import Path

from captionz_core import Settings, Job, make_backend, caption_job

 

s = Settings.load()

s.model = "qwen3-vl:8b"

s.caption_type, s.caption_length = "Training caption (paragraph)", "long"

job = caption_job(Job(Path("photo.jpg")), s, make_backend(s))

print(job.status, job.caption)

Gradio UI API (when "Start (Gradio UI)" is running)

Gradio exposes every event as an endpoint; open <url>/?view=api for the generated docs, or from Python:

 

from gradio_client import Client, handle_file

c = Client("127.0.0.1:7860")

print(c.view_api())

JavaScript (Gradio client)

import { Client } from "@gradio/client";

const c = await Client.connect("127.0.0.1:7860");

console.log(await c.view_api());

Curl (Ollama directly, same request Captionz sends)

curl localhost:11434/api/chat -d '{

"model": "qwen3-vl:8b", "stream": false,

"messages": [{"role": "user", "content": "Describe this image in one short sentence.",

"images": ["<base64 image>"]}]

}'

One year of development has led to this moment: FaceFusion v4 beta is available now, and it is by far the biggest step in the history of the project. To celebrate the release and get developers building on it, we are kicking off the FaceFusion v4 Challenge, where everyone is invited to bring their ideas to life.

 

Cutloom: make a finished short-form video from one topic, on your own PC

 

Cutloom turns a topic into a vertical video for TikTok, YouTube Shorts or Reels. It writes the script, records the voiceover, finds stock footage and adds captions. You can edit every line before you export.

 

How it works

 

Pick a topic (or let it suggest ten).

Write or generate the script, then edit any line.

It matches stock footage to each scene. You can swap clips or use your own.

Choose a voice, captions and optional background music.

Export an MP4.

 

What you need

 

Windows with Pinokio (made and tested on Windows only; Mac and Linux are untested)

No graphics card for the main app

A free Pexels key for stock footage

An OpenAI key is optional. It gives natural AI voices and AI-written scripts, at roughly a few cents per short, billed to you by OpenAI. Without it you can paste your own script and use a free built-in voice.

 

Free and Pro

Free makes 15-second videos at 720p with a small watermark. Pro is $29 one-time, with no subscription. It adds 30 and 60-second videos, 1080p, other shapes (16:9, 1:1, custom), no watermark, background music, batch mode and your own clips. There's also an optional AI-clip add-on that needs Pro.

 

Honest limits

 

Stock footage is matched by keywords, so some scenes will look generic. That's why every scene is editable.

It can't promise views or income. Platforms reduce reach on repetitive videos, so use your own topics and facts.

 

 

I'd love feedback on the install and on the first video you make: what broke, what confused you, and what's missing. Site and pricing: cutloom.netlify.app