What are the hardware requirements for Florence 2 Base PromptGen?

Florence 2 Base PromptGen requires approximately 1.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Florence 2 Base PromptGen and how large is it?

Florence 2 Base PromptGen is developed by MiaoshouAI, a model with 271m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Florence 2 Base PromptGen?

Florence 2 Base PromptGen is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Florence 2 Base PromptGen by MiaoshouAI — VRAM 1.1GB

Name: Florence 2 Base PromptGen
Author: MiaoshouAI

Florence 2 Base PromptGen is an open-source language model by MiaoshouAI. Features: 271m LLM, VRAM: 1.1GB, License: mit, LLM Explorer Score: 0.14.

Autotrain compatible Custom code Florence2 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen

Florence 2 Base PromptGen Parameters and Internals

Model Type

image captioning

Additional Notes

The model is particularly aimed at enhancing image tagging for prompts, providing detailed and accurate captions.

Training Details

Data Sources:

Civitai

Methodology:

Trained for improved tagging experience.

Input Output

Input Format:

instruction prompt

Output Format:

danbooru tagging style

Release Notes

Version:

v0.8

Notes:

New Instruction trained for \

Version:

v0.9

Notes:

Improved vision ability for uncensored data for \

LLM Name	Florence 2 Base PromptGen
Repository 🤗	https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen
Model Size	271m
Required VRAM	1.1 GB
Updated	2025-08-20
Maintainer	MiaoshouAI
Model Type	florence2
Model Files	1.1 GB
Model Architecture	Florence2ForConditionalGeneration
License	mit
Model Max Length	1024
Transformers Version	4.41.0.dev0
Tokenizer Class	BartTokenizer
Padding Token	<pad>
Vocabulary Size	51289
Torch Data Type	float32
Errors	replace

Rank the Florence 2 Base PromptGen capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Florence 2 Base PromptGen

Best Alternatives	Context / RAM	Downloads	Likes
TinyClick	0K / 1.1 GB	421	0
Florence 2 ScreenQA Base	0K / 0.5 GB	10	2

Note: green Score (e.g. "73.2") means that the model is better than MiaoshouAI/Florence-2-base-PromptGen.