---
language: en
license: apache-2.0
tags:
- vision-language-model
- visual-storytelling
- chain-of-thought
- grounded-text-generation
- cross-frame-consistency
- storytelling
- image-to-text
datasets:
- daniel3303/StoryReasoning
metrics:
- precision
- recall
- bleu
- meteor
- rouge
base_model:
- Qwen/Qwen2.5-VL-7B-Instruct
pipeline_tag: image-to-text
model-index:
- name: QwenStoryteller
results:
- task:
type: visual-storytelling
name: Visual Storytelling
dataset:
name: StoryReasoning
type: daniel3303/StoryReasoning
split: test
metrics:
- name: Character Precision
type: precision
value: 0.83
- name: Object Precision
type: precision
value: 0.46
- name: Total Precision
type: precision
value: 0.57
- name: mAP
type: mean_average_precision
value: 0.27
- name: Character Recall
type: recall
value: 0.62
- name: Object Recall
type: recall
value: 0.25
- name: Total Recall
type: recall
value: 0.40
- name: METEOR
type: meteor
value: 0.14
- name: ROUGE-L
type: rouge-l
value: 0.16
- name: BLEU-4
type: bleu-4
value: 0.054
- name: Description Accuracy
type: accuracy
value: 2.76
description: "Rating on a scale of 1-5"
- name: Average Hallucinations
type: error_rate
value: 3.56
description: "Average number of hallucinations per story"
library_name: transformers
---
# QwenStoryteller
QwenStoryteller is a fine-tuned version of Qwen2.5-VL 7B specialized for grounded visual storytelling with cross-frame consistency, capable of generating coherent narratives from multiple images while maintaining character and object identity throughout the story.
## Model Description
**Base Model:** Qwen2.5-VL 7B
**Training Method:** LoRA fine-tuning (rank 2048, alpha 4096)
**Training Dataset:** [StoryReasoning](https://huggingface.co/datasets/daniel3303/StoryReasoning)
QwenStoryteller processes sequences of images to perform:
- End-to-end object detection
- Cross-frame object re-identification
- Landmark detection
- Chain-of-thought reasoning for scene understanding
- Grounded story generation with explicit visual references
The model was fine-tuned on the StoryReasoning dataset using LoRA with a rank of 2048 and alpha scaling factor of 4096, targeting self-attention layers of the language components. Training used a peak learning rate of 1×10⁻⁴ with batch size 32, warmup for the first 3% of steps for 4 epochs, AdamW optimizer with weight decay 0.01, and bfloat16 precision.
## System Prompt
The model was trained with the following system prompt, and we recommend using it as it is for inference.
```
You are an AI storyteller that can analyze sequences of images and create creative narratives.
First think step-by-step to analyze characters, objects, settings, and narrative structure.
Then create a grounded story that maintains consistent character identity and object references across frames.
Use tags to show your reasoning process before writing the final story.
```
## Key Features
- **Cross-Frame Consistency:** Maintains consistent character and object identity across multiple frames through visual similarity and face recognition techniques
- **Structured Reasoning:** Employs chain-of-thought reasoning to analyze scenes with explicit modeling of characters, objects, settings, and narrative structure
- **Grounded Storytelling:** Uses specialized XML tags to link narrative elements directly to visual entities
- **Reduced Hallucinations:** Achieves 12.3% fewer hallucinations compared to the non-fine-tuned base model
## Usage
```python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import torch
from PIL import Image
# Load the model
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
"daniel3303/QwenStoryteller", torch_dtype="auto", device_map="auto"
)
# Load processor
processor = AutoProcessor.from_pretrained("daniel3303/QwenStoryteller")
# Load images
images = [
Image.open("image1.jpg"),
Image.open("image2.jpg"),
Image.open("image3.jpg"),
Image.open("image4.jpg"),
Image.open("image5.jpg")
]
# Create image content list
image_content = []
for img in images:
image_content.append({
"type": "image",
"image": img,
})
# Add text prompt at the end
image_content.append({"type": "text", "text": "Generate a story based on these images."})
# Create messages with system prompt
messages = [
{
"role": "system",
"content": "You are an AI storyteller that can analyze sequences of images and create creative narratives. First think step-by-step to analyze characters, objects, settings, and narrative structure. Then create a grounded story that maintains consistent character identity and object references across frames. Use tags to show your reasoning process before writing the final story."
},
{
"role": "user",
"content": image_content,
}
]
# Preparation for inference
text = processor.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
text=[text],
images=image_inputs,
videos=video_inputs,
padding=True,
return_tensors="pt",
)
inputs = inputs.to(model.device)
# Inference: Generation of the output
generated_ids = model.generate(
**inputs,
max_new_tokens=4096,
do_sample=True,
temperature=0.7,
top_p=0.9
)
generated_ids_trimmed = [
out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
story = processor.batch_decode(
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)[0]
print(story)
```
### Using vLLM for faster inference
For significantly faster inference, you can use vLLM to serve the model. Simply install vLLM and run:
```bash
# Install vLLM
pip install vllm
# Serve the model with vLLM
vllm serve daniel3303/QwenStoryteller
```
## Output Format
QwenStoryteller produces two main outputs:
1. **Chain-of-Thought Analysis (``):** A structured analysis containing:
- Character tables with consistent identity references, emotions, actions, and spatial locations
- Object tables with functions, interactions, and spatial coordinates
- Setting tables categorizing environmental elements
- Narrative structure tables modeling story progression
2. **Grounded Story:** A narrative with specialized XML tags linking text to visual elements:
- ``: Image tags for specific frames
- ``: Entity reference tags for character and object mentions
- ``: Action tags for character actions
- ``: Location/landmark tags for background elements
## Limitations
- Re-identification relies primarily on object appearance rather than overall context, which can lead to confusion with similar-looking objects/persons
- Movie-derived training data introduces biases from cinematic composition that may not generalize to candid visual sequences
- Low grounding rates for first-person pronouns as they primarily appear in character dialogues
- May still produce hallucinations, albeit at a reduced rate compared to the base model
## Citation
```
@misc{oliveira2025storyreasoningdatasetusingchainofthought,
title={StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation},
author={Daniel A. P. Oliveira and David Martins de Matos},
year={2025},
eprint={2505.10292},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2505.10292},
}
```
## Contact
For questions or feedback regarding this model, please contact:
- Daniel A. P. Oliveira (daniel.oliveira@inesc-id.pt)