---
title: fibo-scene-analyzer-gguf
canonical_url: "https://www.modelscope.ai/models/briaai/fibo-scene-analyzer-gguf"
md_url: "https://www.modelscope.ai/models/briaai/fibo-scene-analyzer-gguf.md"
repository: briaai/fibo-scene-analyzer-gguf
last_updated: 2026-10-22
license: cc-by-nc-4.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
base_model:
  - briaai/fibo-scene-analyzer
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 29
stars: 0
tags:
  - gguf
  - llama.cpp
  - scene-analyzer
  - structured-captioning
---

# fibo-scene-analyzer-gguf

> fibo-scene-analyzer-gguf - An open-source model by briaai on ModelScope. FIBO Scene Analyzer — GGUF

briaai/fibo-scene-analyzer-gguf is a image-text-to-text model on ModelScope. licensed under cc-by-nc-4.0. derived from briaai/fibo-scene-analyzer.

- **Repository**: briaai/fibo-scene-analyzer-gguf
- **License**: cc-by-nc-4.0
- **Tasks**: image-text-to-text
- **Base model**: briaai/fibo-scene-analyzer
- **Tags**: gguf, llama.cpp, scene-analyzer, structured-captioning
- **Downloads**: 29
- **Stars**: 0
- **Last updated**: 2026-10-22

Source: https://www.modelscope.ai/models/briaai/fibo-scene-analyzer-gguf

---

# FIBO Scene Analyzer — GGUF

GGUF files of [briaai/fibo-scene-analyzer](https://huggingface.co/briaai/fibo-scene-analyzer) for
[llama.cpp](https://github.com/ggml-org/llama.cpp), with a Python harness that runs every Scene Analyzer task on
`llama-server`. Made and tested with llama.cpp build 11459.

## Start the server

```bash
llama-server -m fibo-scene-analyzer-Q4_K_M.gguf --mmproj mmproj-fibo-scene-analyzer-F16.gguf \
    -ngl 99 -fa on -np 4 -c 131072 --image-max-tokens 8192 --chat-template-kwargs '{"enable_thinking": false}'
```

- `-np` is the number of slots (requests decoded at once). `-c` is the total context of all slots: give each slot
  32,768 tokens, because a full caption with its image can need that much.
- `--image-max-tokens 8192` is the visual-token cap of the model's image processor.
- `--chat-template-kwargs` matters only for the chat endpoint. Without it, llama-server opens a think block in every
  chat prompt.

## Harness

Put the three files of `harness/` on your Python path (they need `pillow`, `pydantic`, `numpy` and, for exact
prompt tokens, `tokenizers`).

```python
from PIL import Image
from scene_analyzer_gguf import DetailLevel, SceneAnalyzerModel, SceneAnalyzerTask, ThinkingEffort

model = SceneAnalyzerModel("http://localhost:8080")
image = Image.open("photo.jpg")

[caption] = model.generate([image], SceneAnalyzerTask.CAPTION, detail_level=DetailLevel.FULL, num_samples=3)
caption.post_process()  # coordinates and colors from tokens to numbers

[objects] = model.generate([image], SceneAnalyzerTask.DETECT, text_inputs=["the red car"])
[text] = model.generate([image], SceneAnalyzerTask.OCR)
[scene] = model.generate([None], SceneAnalyzerTask.EXPAND, text_inputs=["a red fox in fresh snow"], aspect_ratio="1:1")
[reasoned] = model.generate([image], SceneAnalyzerTask.CAPTION, detail_level=DetailLevel.SHORT,
                            thinking_effort=ThinkingEffort.LOW)
```

Or start and stop the server from Python (the `llama-server` binary must be on the `PATH`):

```python
with SceneAnalyzerModel.launch("fibo-scene-analyzer-Q4_K_M.gguf", "mmproj-fibo-scene-analyzer-F16.gguf") as model:
    [caption] = model.generate([image], SceneAnalyzerTask.CAPTION, detail_level=DetailLevel.LONG)
```

`generate()` takes one input per image (`None` for text-only tasks) and returns one answer per input, or `None` for
an input without a valid answer. Inputs run in parallel on the server's slots. Its main arguments:

| Argument | Meaning |
|---|---|
| `task` | `CAPTION`, `DESCRIBE`, `DETECT`, `MASK`, `KEYPOINTS`, `OCR`, `EXPAND`, `EXPAND_OBJECT`, `REFINE`, `EDIT` |
| `detail_level` | `GENERAL`, `SHORT`, `LONG`, `FULL` (captions, expansion, refinement, editing) |
| `text_inputs` | the target to find, the prompt to expand, or the instruction plus the scene JSON |
| `num_samples` | candidates per input; the best valid one is returned |
| `thinking_effort` | `None` for a direct answer, or the effort of a reasoning trace before it |
| `num_iterations` | revision rounds that add the objects the model reports as missing |
| `retries` | extra attempts for inputs without a valid answer |

Constructor options: `seed`, `max_concurrency` (default: the server's slots), `use_grammar` (default on),
`tokenizer` (default `briaai/fibo-scene-analyzer`; set a local folder, or `None` to send text).

What the harness does:

- It sends the trained prompt to llama-server's `/completion` endpoint and samples with temperature 0.6 and top-p
  0.97 only. llama.cpp's defaults also apply top-k 40 and min-p 0.05.
- It constrains each answer to the answer schema with its own GBNF grammar. llama.cpp's JSON-schema converter puts
  the required properties of an object first, which forces the model out of its trained key order and makes it write
  junk. The harness grammar keeps the schema order, lets optional properties be left out in place, and has no free
  whitespace.
- It runs thinking in two passes: the trace without the grammar, then the answer under it.
- It sends text-only prompts as the token ids of the original tokenizer. llama.cpp matches overlapping JSON tokens
  longest-first, so JSON in a prompt can split differently. Prompts with images must be text for llama-server, so
  `edit` and revision rounds keep llama.cpp's tokenization.

## Without the harness

Use llama-server's chat endpoint: the image first, then the task tags, for example `<caption><full>` or
`<detect>the red car`, with `temperature: 0.6, top_p: 0.97, top_k: 0, min_p: 0`. For a reasoning trace, send
`chat_template_kwargs: {"thinking_effort": "low"}`; the trace comes back in `reasoning_content`. Validate the JSON
yourself.