QwenStoryteller-GGUF Open-Source Visual Narrative Model - Supports Consistent Story Generation and Image-to-Text Conversion

Qwenstoryteller GGUF

Developed by mradermacher

Quantized version of Qwen's visual storytelling model, focusing on cross-frame consistent story generation and image-to-text tasks

Image-to-Text EnglishOpen Source License:Apache-2.0 #Visual Storytelling Generation #Cross-frame Consistency #Chain-of-Thought Reasoning

Downloads 195

Release Time : 5/13/2025

Model Overview

This model is a statically quantized version of QwenStoryteller, specifically optimized for visual storytelling capabilities, supporting coherent story text generation from image inputs while maintaining cross-frame consistency.

Model Features

Cross-frame Consistency

Maintains story coherence and logical consistency when generating descriptions for multiple frames

Chain-of-Thought Support

Supports chain-of-thought reasoning to generate more logically coherent narrative content

Multiple Quantization Options

Provides 12 quantization versions from Q2_K to f16 to meet different hardware and precision requirements

Visual Language Understanding

Capable of understanding image content and converting it into expressive textual descriptions

Model Capabilities

Image-to-text generation

Visual storytelling

Coherent story creation

Multimodal understanding

Use Cases

Content Creation

Comic Script Generation

Automatically generates coherent dialogues and narrations based on comic panel images

Scripts that maintain character personalities and plot coherence

Educational Storytelling

Converts educational illustrations into story texts suitable for children's reading

Entertaining and educational story content

Creative Assistance

Film Storyboard Description

Generates detailed scene descriptions for film storyboards

Detailed scene descriptions usable for scriptwriting

🚀 QwenStoryteller Quantized Model

This project offers static quantizations of the QwenStoryteller model, providing various quantized versions for different usage scenarios. It enables efficient deployment and utilization of the model.

🚀 Quick Start

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi - part files.

✨ Features

Multiple Quantization Types: Offers a range of quantized versions of the QwenStoryteller model, sorted by size.
Visual Comparison: Provides a graph comparing some lower - quality quant types.
Community Insights: Shares external thoughts on the quantization matter.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

No code examples are provided in the original document.

📚 Documentation

About

Static quants of https://huggingface.co/daniel3303/QwenStoryteller. Weighted/imatrix quants are available at https://huggingface.co/mradermacher/QwenStoryteller-i1-GGUF.

Provided Quants

(sorted by size, not necessarily quality. IQ - quants are often preferable over similar sized non - IQ quants)

Link	Type	Size/GB	Notes
GGUF	Q2_K	3.1
GGUF	Q3_K_S	3.6
GGUF	Q3_K_M	3.9	lower quality
GGUF	Q3_K_L	4.2
GGUF	IQ4_XS	4.4
GGUF	Q4_K_S	4.6	fast, recommended
GGUF	Q4_K_M	4.8	fast, recommended
GGUF	Q5_K_S	5.4
GGUF	Q5_K_M	5.5
GGUF	Q6_K	6.4	very good quality
GGUF	Q8_0	8.2	fast, best quality
GGUF	f16	15.3	16 bpw, overkill

Here is a handy graph by ikawrakow comparing some lower - quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

🔧 Technical Details

No specific technical details are provided in the original document.

📄 License

The model is licensed under the apache - 2.0 license.

👏 Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Information Table

Property	Details
Base Model	daniel3303/QwenStoryteller
Datasets	daniel3303/StoryReasoning
Language	en
Library Name	transformers
License	apache - 2.0
Quantized By	mradermacher
Tags	vision - language - model, visual - storytelling, chain - of - thought, grounded - text - generation, cross - frame - consistency, storytelling, image - to - text

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご