RRepoGEO

REPOGEO REPORT · LITE

PKU-YuanGroup/ConsisID

Default branch main · commit 60429e4b · scanned 6/14/2026, 1:33:15 AM

GitHub: 846 stars · 45 forks

AI VISIBILITY SCORE
33 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 warn · 0 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface PKU-YuanGroup/ConsisID, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition the README's opening statement for clarity

    Why:

    CURRENT
    This repository is the official implementation of ConsisID, a tuning-free DiT-based controllable IPT2V model to keep human-identity consistent in the generated video.
    COPY-PASTE FIX
    ConsisID is the official implementation for **identity-preserving text-to-video generation**, a tuning-free DiT-based model designed to maintain consistent human identity in generated videos.
  • highreadme#2
    Expand the README's initial description with a 'Key Features' section

    Why:

    COPY-PASTE FIX
    ## Key Features
- **Identity Preservation:** Ensures consistent human identity across generated video frames.
- **Tuning-Free:** Operates without requiring extensive fine-tuning.
- **DiT-based Architecture:** Leverages advanced Diffusion Transformers for high-quality generation.
- **Frequency Decomposition:** Utilizes a novel approach for enhanced consistency.
  • mediumreadme#3
    Add a 'Comparison' or 'Why ConsisID?' section to the README

    Why:

    COPY-PASTE FIX
    ## Why ConsisID? (or ConsisID vs. Others)
Unlike many existing text-to-video tools that struggle with identity consistency or require extensive fine-tuning, ConsisID offers a tuning-free, model-agnostic solution for robust identity preservation. This makes it particularly suitable for research and applications requiring high fidelity in character representation.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface PKU-YuanGroup/ConsisID
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
RunwayML Gen-2
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. RunwayML Gen-2 · recommended 2×
  2. Pika Labs · recommended 2×
  3. HeyGen · recommended 2×
  4. Stable Video Diffusion · recommended 1×
  5. Midjourney · recommended 1×
  • CATEGORY QUERY
    How to generate high-quality videos from text prompts, ensuring consistent character identity?
    you: not recommended
    AI recommended (in order):
    1. RunwayML Gen-2
    2. Pika Labs
    3. Stable Video Diffusion
    4. Midjourney
    5. Stable Diffusion
    6. D-ID Creative Reality Studio
    7. After Effects
    8. HeyGen
    9. Synthesia

    AI recommended 9 alternatives but never named PKU-YuanGroup/ConsisID. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for a text-to-video generation tool that preserves character identity without fine-tuning.
    you: not recommended
    AI recommended (in order):
    1. RunwayML Gen-2
    2. Pika Labs
    3. HeyGen
    4. DeepMotion
    5. Synthesys AI Studio

    AI recommended 5 alternatives but never named PKU-YuanGroup/ConsisID. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of PKU-YuanGroup/ConsisID?
    pass
    AI named PKU-YuanGroup/ConsisID explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts PKU-YuanGroup/ConsisID in production, what risks or prerequisites should they evaluate first?
    pass
    AI named PKU-YuanGroup/ConsisID explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo PKU-YuanGroup/ConsisID solve, and who is the primary audience?
    pass
    AI did not name PKU-YuanGroup/ConsisID — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of PKU-YuanGroup/ConsisID. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/PKU-YuanGroup/ConsisID.svg)](https://repogeo.com/en/r/PKU-YuanGroup/ConsisID)
HTML
<a href="https://repogeo.com/en/r/PKU-YuanGroup/ConsisID"><img src="https://repogeo.com/badge/PKU-YuanGroup/ConsisID.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

PKU-YuanGroup/ConsisID — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite