Cdf anomalygen vs Tao generate anomalies
Cdf anomalygen is an open-source agent skill for design and media. Tao generate anomalies is an open-source agent skill for ai models and llm tooling.
- Cdf anomalygen is best for run the anomalygen pipeline on a phone screen defect dataset.
- Tao generate anomalies is best for fine-tune anomalygen on a new set of defect images.
- What it is
- Cdf anomalygen is an open-source agent skill for design and media.Tao generate anomalies is an open-source agent skill for ai models and llm tooling.
- Best for
- Run the AnomalyGen pipeline on a phone screen defect datasetFine-tune AnomalyGen on a new set of defect images
- Kind
- SkillSkill
- Pricing
- Open sourceOpen source
- Platforms
- Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, GooseClaude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf, Goose
- GitHub stars
- 4K4K
- Last commit
- Nov 2026Nov 2026
- License
- Apache-2.0Apache-2.0
- Open source
- Good for
- Run the AnomalyGen pipeline on a phone screen defect dataset; Fine-tune an anomaly-generation model for PCB defects; Generate 25 synthetic defect images from an existing checkpointFine-tune AnomalyGen on a new set of defect images; Generate a batch of synthetic anomaly images from an existing checkpoint; Evaluate the quality of previously generated anomaly images
What Cdf anomalygen does
Dataset layout validation
Checks that clean images, defect images and masks follow the expected folder contract before any stage runs.
Mask placement backends
Places defect masks either through a vision-language model agent loop or a classic allocation and pairing pipeline.
Model fine-tuning
Runs a detached fine-tune from a recipe, with checkpoint selection from validation KPIs.
Synthetic defect generation
Produces defect images from a checkpoint and testcase file, with guardrail-blocked samples logged separately.
KPI evaluation
Scores generated batches against real data using nearest-neighbour and related metrics.
Quality refinement and labeling
Runs search rounds to refine outputs, then exports COCO annotations and classification layouts.
What Tao generate anomalies does
Model fine-tuning
Trains the AnomalyGen model on a user-supplied anomaly dataset with configurable iterations, learning rate and batch size.
Synthetic anomaly generation
Produces synthetic defect images from a checkpoint using a defect specification file.
Quality evaluation
Scores generated images with nn_score and writes per-sample CSV and aggregate eval logs.
Per-sample parameter search
Runs search rounds over guidance and crop ratio to pick the best result for each sample.
Threshold filtering and regeneration
Drops samples below an nn_score threshold and regenerates replacements to fill the target count.
Guardrail-aware output checks
Flags images blocked by a content-safety check so they are not passed downstream.
Cdf anomalygen vs Tao generate anomalies: questions
Is Cdf anomalygen or Tao generate anomalies cheaper?
Both are open source. Compare current plans on each official site.
What is the difference between Cdf anomalygen and Tao generate anomalies?
Cdf anomalygen is an open-source agent skill for design and media. Tao generate anomalies is an open-source agent skill for ai models and llm tooling.
