REPOGEO REPORT · LITE

adobe-research/custom-diffusion

Default branch main · commit 7c19c9a7 · scanned 6/20/2026, 11:47:55 PM

GitHub: 1,974 stars · 141 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

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 adobe-research/custom-diffusion, 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 H1 to highlight multi-concept customization and efficiency
Why:
CURRENT
```
# Custom Diffusion
```
COPY-PASTE FIX
```
# Custom Diffusion: Efficient Multi-Concept Customization for Text-to-Image Diffusion
```

mediumlicense#2

Add a clear statement about the project's license to the README

Why:

COPY-PASTE FIX

This project is licensed under [specify license name(s) here, e.g., a custom research license or a combination of licenses]. Please refer to the LICENSE file for full details.

lowtopics#3

Add more specific topics to reinforce unique capabilities

Why:

CURRENT

computer-vision, customization, diffusion-models, few-shot, fine-tuning, pytorch, text-to-image-generation

COPY-PASTE FIX

computer-vision, customization, diffusion-models, few-shot, fine-tuning, pytorch, text-to-image-generation, multi-concept, efficient-finetuning

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 adobe-research/custom-diffusion

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

huggingface/diffusers

Recommended in 3 of 2 queries

COMPETITOR LEADERBOARD

huggingface/diffusers · recommended 3×
bmaltais/kohya_ss · recommended 1×
RunDiffusion · recommended 1×
Civitai · recommended 1×
Google Colab · recommended 1×

CATEGORY QUERY
How can I fine-tune a text-to-image model with only a few custom images?
you: not recommended
AI recommended (in order):
1. DreamBooth (huggingface/diffusers)
2. LoRA (huggingface/diffusers)
3. Textual Inversion (huggingface/diffusers)
4. Kohya's GUI (bmaltais/kohya_ss)
5. RunDiffusion
6. Civitai
7. Google Colab
AI recommended 7 alternatives but never named adobe-research/custom-diffusion. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What tools allow combining multiple custom concepts in text-to-image generation efficiently?
you: not recommended
AI recommended (in order):
1. Automatic1111 Stable Diffusion WebUI (AUTOMATIC1111/stable-diffusion-webui)
2. ControlNet (lllyasviel/ControlNet)
3. LoRA
4. LyCORIS (KohakuBlueleaf/LyCORIS)
5. Textual Inversion
6. Regional Prompter (hako-mikan/sd-webui-regional-prompter)
7. Latent Couple
8. Dynamic Prompts (adieyal/sd-dynamic-prompts)
9. ComfyUI (comfyanonymous/ComfyUI)
10. Fooocus (lllyasviel/Fooocus)
11. InvokeAI (invoke-ai/InvokeAI)
12. Leonardo.Ai
13. Midjourney
AI recommended 13 alternatives but never named adobe-research/custom-diffusion. 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 adobe-research/custom-diffusion?
pass
AI named adobe-research/custom-diffusion explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts adobe-research/custom-diffusion in production, what risks or prerequisites should they evaluate first?
pass
AI named adobe-research/custom-diffusion 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 adobe-research/custom-diffusion solve, and who is the primary audience?
pass
AI named adobe-research/custom-diffusion 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 adobe-research/custom-diffusion. 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/adobe-research/custom-diffusion.svg)](https://repogeo.com/en/r/adobe-research/custom-diffusion)

HTML

<a href="https://repogeo.com/en/r/adobe-research/custom-diffusion"><img src="https://repogeo.com/badge/adobe-research/custom-diffusion.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

adobe-research/custom-diffusion — 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