# freestylefly/awesome-gpt-image-2

> A prompt and template library for GPT-Image 2/2.5 image generation: 500+ reverse-engineered cases, 20+ industrial templates and an agent Skill, structured as Prompt-as-Code.

- Magnitude: 2.6 out of 10 — Steady
- Stars: 34,847 total · +65 stars measured 2026-10-21, 00:08–21:51 UTC, ≈ 71 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: JavaScript · License: MIT · Created: 2026-04-25 · Last push: 2026-10-14
- GitHub: https://github.com/freestylefly/awesome-gpt-image-2 · Homepage: https://gpt-image2.canghe.ai · Page: https://gitnova.dev/en/r/freestylefly/awesome-gpt-image-2

## Useful for

- Find a ready prompt for a specific style or scenario in the case gallery
- Build a structured prompt template for batch image generation
- Plug the style library Skill into an agent to automate prompting

## Why it’s here

- Star-counter measurements on 2026-10-21 (UTC), 00:08–21:51: 34782 → 34847 stars (+65). This is the change over that interval.
- Estimated end-of-day forecast: about +71 stars, using observed gains and the previous day.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3,311
- Issues and pull requests: 41
- Watchers: 142
- Average over the last week: 58 per day
- Usual pace: 88 per day

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 56, 35, 36, 42, 40, 41, 43, 53, 67, 114, 46, 46, 83, 63, 61, 54, 50, 49, 59, 63, 62, 41, None, None, None, None, None, None, None, None

## Magnitude by day, last 14 days

10-03 2.0, 10-04 2.1, 10-10 2.8, 10-11 2.5, 10-12 2.7, 10-13 3.0, 10-14 2.8, 10-15 2.7, 10-16 2.6, 10-17 2.6, 10-18 2.4, 10-19 2.6, 10-20 2.7, 10-21 2.6

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-21 21:58 UTC, updated every 30 minutes.