← back to catalog · registered 2026-08-22 13:56

UncensoredAI123/scidraw

Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/UncensoredAI123%2Fscidraw"
Response includes
  • classification unknown
  • files 2
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
?
Primary method

Unclassified

No clear signals of an abliteration technique in this model.
Confidence
UNKNOWN
Why this label 1 signal
No classification signals present. This may not be an abliterated model at all - it could be a repackaging, a merge with unrelated goals, or unrelated content that mentions the term.
  • no classification signals present (no abliterated, uncensored, or known producer/method markers)
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
1
Model age
8mo ago
created 2026-01-15

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now0→from0↑0%
00110 on Jan 140 on Oct 11JanMarMayJulSep
Jan 14 → Oct 11 · 78 snapshots · spans 270 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Languages
en
Tags
flair graph-ml en dataset:bigai/TongSIM-Asset base_model:TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill-GGUF base_model:finetune:TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill-GGUF license:apache-2.0 region:us
Total size
0 B
Files
2
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-28 14:10

Files by quantization

Auxiliary files 2 files 5.26 KB
README.md 3.78 KB 7c34b244 download
.gitattributes 1.48 KB a6344aac download

README current version from Hugging Face


license: apache-2.0
datasets:

  • bigai/TongSIM-Asset
    language:
  • en
    metrics:
  • character
    base_model:
  • TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill-GGUF
    new_version: zai-org/GLM-Image
    pipeline_tag: graph-ml
    library_name: flair

🎨 SciDraw AI - Scientific Illustration Generator

Website
Users

Create publication-ready scientific figures in seconds, not days.

🔬 What is SciDraw AI?

SciDraw AI is an AI-powered platform that generates scientific illustrations for researchers. Describe what you need or upload a rough sketch — get journal-quality figures instantly.

Built for: PhD students, postdocs, research labs, and anyone who needs professional scientific figures without the design skills.

✨ Key Features

Feature Description
🖼️ Text-to-Image Describe your scientific concept → AI generates illustration
✏️ Sketch-to-Image Upload rough drawing → AI transforms to professional figure
🔄 Multi-round Editing Refine through conversation until perfect
📐 SVG Vector Export Editable in Illustrator/PowerPoint/Inkscape
🎨 7+ Templates TOC graphics, journal covers, pathways, mechanisms
🌈 6+ Visual Styles Flat, 3D, photorealistic, schematic

🚀 Use Cases

  • TOC Graphics - Table of Contents figures for journals
  • Graphical Abstracts - Visual summaries for papers
  • Journal Covers - Nature/Science/Cell style covers
  • Pathway Diagrams - Cell signaling, metabolic pathways
  • Mechanism Illustrations - Molecular mechanisms, drug delivery
  • Experimental Workflows - Protocol visualizations

📊 Example Prompts

"DNA double helix with CRISPR-Cas9 protein, Nature journal style"

"Cell signaling pathway from receptor to nucleus, flat illustration, 
blue and orange color scheme"

"Nanoparticle drug delivery system targeting cancer cells, 
3D rendered style"

"Protein folding mechanism showing primary to quaternary structure"

🎯 Why SciDraw AI?

Problem SciDraw AI Solution
Figures take days/weeks Generate in seconds
Need design skills Zero learning curve
Expensive designers ($300/fig) Free tier available
Generic AI = bad science art Trained for scientific accuracy
Raster images = no editing SVG vector = fully editable

📈 Stats

  • 10,000+ researchers worldwide
  • 90% time savings vs traditional methods
  • 95% cost reduction vs hiring designers
  • Used at Stanford, MIT, Harvard, Oxford, ETH Zurich

🆓 Try Free

  • 10 credits on signup
  • 5 free credits daily
  • No credit card required

🔗 Links


🛠️ Technical Details

SciDraw AI combines multiple AI models fine-tuned specifically for scientific illustration:

  • Domain-specific training on scientific figures from major journals
  • Style transfer capabilities for consistent visual language
  • Vector generation pipeline for SVG output
  • Multi-modal input supporting text, sketches, and reference images

📄 Citation

If you use SciDraw AI in your research, please consider mentioning us:

Figures created with SciDraw AI (https://sci-draw.com)

Questions or feedback? Reach out at [email protected]

Try SciDraw AI Free

README history 3 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-05-28Update README.md98355283.8 KB
    Loading...
  2. 2026-01-15Update README.md50d3a5b3.8 KB
    Loading...
  3. 2026-01-15Create README.mdec800d43.5 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration