# TencentARC/Looking-Ahead

> Code and weights for autoregressive video generation: the Future Chunk Prediction (FCP) method trains models to predict future video chunks, improving physical consistency. Includes training and inference for 1.3B and 5B TI2V models.

- Magnitude: 1.2 out of 10 — Cooling
- Stars: 121 total · +1 star measured 2026-10-27, 00:34–02:09 UTC, ≈ 8 by evening
- Star trust: star growth looks organic
- Category: Generative media · Language: Python · Created: 2026-10-21 · Last push: 2026-10-26
- GitHub: https://github.com/TencentARC/Looking-Ahead · Homepage: https://hellorpg.github.io/looking-ahead/ · Page: https://gitnova.dev/en/r/TencentARC/Looking-Ahead

## Useful for

- Generate a 5-second video from an image and text prompt with the 1.3B model
- Continue an existing video from a text prompt using the 5B model
- Compare the TF baseline and FCP method on identical prompts

## Why it’s here

- Star-counter measurements on 2026-10-27 (UTC), 00:34–02:09: 120 → 121 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +8 stars, using observed gains and the previous day.
- The repository is 6 days old and already has 121 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #191.

## 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: 2
- Issues and pull requests: 4
- Watchers: 3
- Average over the last week: 18 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 7 days (oldest → newest, today is partial)

2026-10-21 … 2026-10-27: 32, 43, 15, 8, 16, 7, 1

## Spotted in now

- Top new repositories this week: #191

## More in this category

1. **wlnhnoqefoxt/adult-ai-video** — 6.6 · Early signal · Generative media · Python · +0 stars measured 2026-10-27, 00:34–02:01 UTC, ≈ 167 by evening
   Portable desktop NSFW video generator running a local diffusion pipeline: text-to-video and image-to-video with up to 4K output, no install and no network calls.
   Full card: https://gitnova.dev/en/r/wlnhnoqefoxt/adult-ai-video.md
2. **Vibha-Ramprakash/claude-video-effects** — 5.6 · Early signal · Generative media · Python · +5 stars measured 2026-10-27, 00:34–02:01 UTC, ≈ 114 by evening
   A set of 42 video effects for Claude Code: drop a talking-head clip into the chat and type /effects with an effect name — Claude renders the result with face tracking.
   Full card: https://gitnova.dev/en/r/Vibha-Ramprakash/claude-video-effects.md
3. **debpalash/VoiceStudio** — 5.3 · Steady · Generative media · Python · +154 stars measured 2026-10-27, 00:34–02:01 UTC, ≈ 1,950 by evening
   A fully local, open-source ElevenLabs alternative for voice cloning, voice design, video dubbing, dictation, transcription and audiobook creation on your own hardware, with no account or API key. Supports 16 TTS and 11 ASR engines, a…
   Full card: https://gitnova.dev/en/r/debpalash/VoiceStudio.md
4. **higgsfield-ai/skills** — 4.7 · Breakout · Generative media · Python · +5 stars measured 2026-10-27, 00:34–02:01 UTC, ≈ 62 by evening
   A set of Markdown skills for AI coding agents (Claude Code, Cursor, Codex) that use Higgsfield AI to generate images, video, audio, and 3D, and to build visual brand systems and ad creatives.
   Full card: https://gitnova.dev/en/r/higgsfield-ai/skills.md
5. **heygen-com/hyperframes** — 4.6 · Steady · Generative media · TypeScript · +63 stars measured 2026-10-27, 00:34–02:01 UTC, ≈ 734 by evening
   Framework for turning HTML, CSS, media and seekable animations into deterministic MP4 videos. Runs locally via CLI or from AI coding agents through a set of skills.
   Full card: https://gitnova.dev/en/r/heygen-com/hyperframes.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 2026-10-27 02:12 UTC, updated every 30 minutes.