REPOGEO REPORT · LITE

dome272/Wuerstchen

Default branch main · commit a3a8a2af · scanned 6/16/2026, 9:28:00 AM

GitHub: 556 stars · 34 forks

AI VISIBILITY SCORE

40 /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

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 dome272/Wuerstchen, 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

hightopics#1

Add more specific topics for text-to-image and compression

Why:

CURRENT

diffusion-models, efficiency, machine-learning, stable-diffusion

COPY-PASTE FIX

diffusion-models, efficiency, machine-learning, stable-diffusion, text-to-image, image-generation, latent-diffusion, image-compression

highreadme#2

Add a concise, keyword-rich tagline under the main H1

Why:

CURRENT

# Würstchen (ICLR 2024, oral)

COPY-PASTE FIX

# Würstchen (ICLR 2024, oral)

**The highly compressed, computationally efficient framework for text-to-image generation.**

mediumreadme#3

Enhance 'What is this?' section with a direct comparison statement

Why:

CURRENT

Common approaches make use of a single stage compression, while Würstchen introduces another Stage that introduces even more compression. In total we have Stage A & B that are responsible for compressing images and Stage C that learns the text-conditional part in the low dimensional latent space. With that Würstchen achieves a 42x compression factor, while still reconstructing images faithfully. This enables training of Stage C to be fast and computationally cheap. We refer to the paper for details.

COPY-PASTE FIX

Common approaches make use of a single stage compression, while Würstchen introduces another Stage that introduces even more compression. In total we have Stage A & B that are responsible for compressing images and Stage C that learns the text-conditional part in the low dimensional latent space. With that Würstchen achieves a 42x compression factor, while still reconstructing images faithfully. This enables training of Stage C to be fast and computationally cheap. Unlike many common text-to-image models, this multi-stage architecture offers significantly faster training and computationally cheaper generation. We refer to the paper for details.

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 dome272/Wuerstchen

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

Stable Diffusion

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

Stable Diffusion · recommended 2×
DeepSpeed · recommended 1×
PyTorch FSDP · recommended 1×
bitsandbytes · recommended 1×
LoRA · recommended 1×

CATEGORY QUERY
How can I train text-to-image diffusion models more efficiently with high compression?
you: not recommended
AI recommended (in order):
1. Stable Diffusion
2. DeepSpeed
3. PyTorch FSDP
4. bitsandbytes
5. LoRA
6. DreamBooth
7. Textual Inversion
8. xFormers
9. Diffusers library (Hugging Face)
AI recommended 9 alternatives but never named dome272/Wuerstchen. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What are the best approaches for computationally cheap text-conditional image generation?
you: not recommended
AI recommended (in order):
1. Stable Diffusion
2. SD-Tiny
3. LCM-LoRA
4. DeepFloyd IF
5. Mini-DALL-E
6. GLIDE
7. VQGAN+CLIP
AI recommended 7 alternatives but never named dome272/Wuerstchen. 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 dome272/Wuerstchen?
pass
AI named dome272/Wuerstchen explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts dome272/Wuerstchen in production, what risks or prerequisites should they evaluate first?
pass
AI named dome272/Wuerstchen 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 dome272/Wuerstchen solve, and who is the primary audience?
pass
AI named dome272/Wuerstchen 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 dome272/Wuerstchen. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/dome272/Wuerstchen.svg)](https://repogeo.com/en/r/dome272/Wuerstchen)

HTML

<a href="https://repogeo.com/en/r/dome272/Wuerstchen"><img src="https://repogeo.com/badge/dome272/Wuerstchen.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

dome272/Wuerstchen — 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