Synthetic-Cyclic-Perception_exp1

[<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png" width="200"/>](https://devquasar.com)

'Make knowledge free for everyone'

<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>

# Synthetic-Cyclic-Perception


Synthetic-Cyclic-Perception is a synthetic visual dataset created by iteratively generating and describing images in a cyclic fashion. Each cycle begins with a seed prompt that feeds into a diffusion model to generate an initial image. A vision model then provides a detailed description of the generated image, which becomes the prompt for the next cycle. This process is repeated across multiple cycles and batches, creating a dataset where images and their descriptions evolve progressively.

## Dataset Composition

- Seed Prompts: The dataset generation starts with carefully selected, action-oriented prompts (e.g., “A person kayaking on a calm river”).
- Cycles: Each batch begins with a unique prompt and progresses through a set number of cycles, updating the image based on the most recent description.
- Metadata: Each image generated includes metadata such as the prompt, the vision model's description, filename, and batch details, saved in a centralized metadata JSON file for easy reference and analysis.

## Methodology

- Image Generation: Using the [stabilityai/stable-diffusion-3-medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium) model, an image is generated based on the current prompt.
- Vision Description: The [meta-llama/Llama-3.2-11B-Vision-Instruct](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct) describes the image, offering a nuanced textual interpretation.
- Cyclic Prompt Update: The description is parsed and used as the next prompt in the cycle, thus creating an evolving image-description sequence.

[<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png" width="200"/>](https://devquasar.com)

"让知识惠及每一个人"

<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='在ko-fi上为我买一杯咖啡' /></a>

# 合成循环感知（Synthetic-Cyclic-Perception）


合成循环感知（Synthetic-Cyclic-Perception）是一种通过循环迭代生成与描述图像的方式构建的合成视觉数据集。每一轮循环均以种子提示词（Seed Prompts）为起点，将其输入扩散模型（diffusion model）以生成初始图像；随后由视觉模型（vision model）对生成的图像进行详细描述，该描述将作为下一轮循环的提示词。该流程经多轮循环与多批次重复执行，最终构建出图像与描述持续渐进演化的数据集。

## 数据集构成
- 种子提示词（Seed Prompts）：数据集生成以精心筛选的行动导向型提示词为起点，例如“一名正在平静河面上划皮划艇的人”。
- 循环（Cycles）：每个批次均以独特的提示词为起点，经过预设数量的循环迭代，基于最新的描述更新图像。
- 元数据（Metadata）：每张生成的图像均附带元数据，包括提示词、视觉模型生成的描述、文件名以及批次信息，这些元数据将保存至中心化的元数据JSON文件中，便于查阅与分析。

## 构建方法
- 图像生成：基于当前提示词，使用[stabilityai/stable-diffusion-3-medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium)模型生成图像。
- 视觉描述：使用[meta-llama/Llama-3.2-11B-Vision-Instruct](https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct)对图像进行描述，输出细致入微的文本解读。
- 循环提示词更新：将生成的描述文本解析后作为下一轮循环的提示词，由此形成持续演化的图像-描述序列。