# MiniMax-AI/MiniMax-H3-Image

> MiniMax-H3-Image is an open-weight model for text-to-image generation and editing at about 16 MP, using up to 16 reference images and no upscaler.

- Magnitude: 3.1 out of 10 — Cooling
- Stars: 350 total · +10 stars measured 2026-11-14, 00:04–11:15 UTC, ≈ 23 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · Created: 2026-11-09 · Last push: 2026-11-11
- GitHub: https://github.com/MiniMax-AI/MiniMax-H3-Image · Page: https://gitnova.dev/en/r/MiniMax-AI/MiniMax-H3-Image

## Useful for

- Generate a 3:4 poster from a short brief via the skill in Claude Code or Cursor
- Compose an image from 10 references with coordinated outfit colors
- Render an illustration through the MiniMax API using MINIMAX_API_KEY

## Why it’s here

- Star-counter measurements on 2026-11-14 (UTC), 00:04–11:15: 340 → 350 stars (+10). This is the change over that interval.
- Estimated end-of-day forecast: about +23 stars, using observed gains and the previous day.
- The repository is 5 days old and already has 350 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #34.

## 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: 19
- Issues and pull requests: 6
- Watchers: 0
- Average over the last week: 62 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 6 days (oldest → newest, today is partial)

2026-11-09 … 2026-11-14: 0, 127, 126, 69, 27, 10

## Magnitude by day, last 3 days

11-12 5.4, 11-13 4.3, 11-14 3.1

## Spotted in now

- Top new repositories this week: #34

## More in this category

1. **Forward-Future/scarlet** — 5.7 · Early signal · Generative media · TypeScript · +36 stars measured 2026-11-14, 05:40–11:13 UTC, ≈ 102 by evening
   Open-source AI video editor for macOS, Windows and Linux: you ask Claude Code or Codex by voice or text to change a recording, and Scarlet plays the edit on the timeline while keeping original footage intact.
   Full card: https://gitnova.dev/en/r/Forward-Future/scarlet.md
2. **higurashi-ai/Haru** — 5.3 · Early signal · Generative media · Python · +35 stars measured 2026-11-14, 00:03–11:13 UTC, ≈ 93 by evening
   Inference code for Haru-4B, a multilingual full-duplex spoken dialogue model that listens and speaks at the same time, like on a phone call. Includes PyTorch, MLX and vLLM-Omni implementations plus a web demo.
   Full card: https://gitnova.dev/en/r/higurashi-ai/Haru.md
3. **jamesondh/chimera-vocal-synth** — 5.3 · Cooling · Generative media · Rust · +61 stars measured 2026-11-14, 00:03–11:13 UTC, ≈ 130 by evening
   A browser-based vocal synthesizer built on physical modeling: sound comes from a simulated airway rather than samples. The Rust engine compiles to WebAssembly for an AudioWorklet and also runs natively via a CLI.
   Full card: https://gitnova.dev/en/r/jamesondh/chimera-vocal-synth.md
4. **brave-plum-co/leonardo-ai-desktop** — 5.1 · Early signal · Generative media · C++ · +103 stars measured 2026-11-14, 06:23–11:13 UTC, ≈ 157 by evening
   Standalone offline Windows x64 build of the Leonardo AI image-generation workflow, bundling the diffusion runtime, model cache loader and portable launcher for air-gapped or batch-provisioned workstations.
   Full card: https://gitnova.dev/en/r/brave-plum-co/leonardo-ai-desktop.md
5. **linknimiball1974/ai-texture-forge** — 4.8 · Early signal · Generative media · +60 stars measured 2026-11-14, 00:03–11:13 UTC, ≈ 123 by evening
   A Blender add-on that generates seamless PBR textures, concept art and scene projections from text prompts using local or cloud diffusion models directly in the 3D viewport.
   Full card: https://gitnova.dev/en/r/linknimiball1974/ai-texture-forge.md

---

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 2026-11-14 11:22 UTC, updated every 30 minutes.