RRepoGEO

REPOGEO REPORT · LITE

thu-ml/unidiffuser

Default branch main · commit 845e14f7 · scanned 6/20/2026, 1:33:15 PM

GitHub: 1,484 stars · 91 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
35 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
3 / 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 thu-ml/unidiffuser, 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

2 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 to highlight the core problem and solution

    Why:

    CURRENT
    Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"
    COPY-PASTE FIX
    UniDiffuser is a unified diffusion framework that enables a single transformer model to fit all distributions relevant to multi-modal data, allowing for diverse generative tasks like image, text, and image-text pair generation.
  • mediumhomepage#2
    Add a homepage URL to the repository metadata

    Why:

    COPY-PASTE FIX
    https://thu-ml.github.io/unidiffuser/

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 thu-ml/unidiffuser
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Hugging Face Transformers
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Hugging Face Transformers · recommended 1×
  2. Diffusers · recommended 1×
  3. PEFT · recommended 1×
  4. Google's Pathways Language Model (PaLM) · recommended 1×
  5. Gemini · recommended 1×
  • CATEGORY QUERY
    How can I build a single generative model for diverse multi-modal content creation?
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers
    2. Diffusers
    3. PEFT
    4. Google's Pathways Language Model (PaLM)
    5. Gemini
    6. OpenAI's GPT-4 with Vision
    7. DALL-E 3
    8. Meta's ImageBind
    9. Microsoft's Kosmos-1
    10. Kosmos-2
    11. PyTorch
    12. TensorFlow

    AI recommended 12 alternatives but never named thu-ml/unidiffuser. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are the best transformer-based diffusion models for unified multi-distribution learning?
    you: not recommended
    AI recommended (in order):
    1. DiT (Diffusion Transformers)
    2. U-ViT (U-shaped Vision Transformer)
    3. PixArt-$α$
    4. Latent Diffusion Models (LDM)
    5. Stable Diffusion v3
    6. Masked Autoencoders (MAE)
    7. VQ-Diffusion

    AI recommended 7 alternatives but never named thu-ml/unidiffuser. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    warn

    Suggestion:

  • 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 thu-ml/unidiffuser?
    pass
    AI named thu-ml/unidiffuser explicitly

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

  • If a team adopts thu-ml/unidiffuser in production, what risks or prerequisites should they evaluate first?
    pass
    AI named thu-ml/unidiffuser 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 thu-ml/unidiffuser solve, and who is the primary audience?
    pass
    AI named thu-ml/unidiffuser explicitly

    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 thu-ml/unidiffuser. 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/thu-ml/unidiffuser.svg)](https://repogeo.com/en/r/thu-ml/unidiffuser)
HTML
<a href="https://repogeo.com/en/r/thu-ml/unidiffuser"><img src="https://repogeo.com/badge/thu-ml/unidiffuser.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

thu-ml/unidiffuser — 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