ML Models
BurstPick supports 20+ on-device model providers across 6 categories. Built-in models run without setup; larger model families download on demand and require Pro. Photos are not uploaded for analysis.
Image Quality Assessment
Scores each photo on sharpness, noise, exposure, and perceptual clarity. Used to rank photos within burst clusters.
Heuristic (Laplacian + Luma)
BundledInstant scoring using Accelerate vDSP/vImage. Measures sharpness, exposure, noise, and eye closure. Cannot judge composition or semantic quality. Best for fast initial culling passes.
TOPIQ NR
No-reference IQA using ResNet50 backbone. General-purpose technical quality scoring.
MUSIQ (KonIQ)
Multi-scale transformer trained on KonIQ-10k real-world distortions. Used for natural-photo quality assessment.
MANIQA
NTIRE 2022 IQA Challenge winner. Multi-dimension attention captures fine perceptual differences. Larger than the other bundled IQA options.
NIMA (MobileNet)
Neural Image Assessment trained on AVA (250K aesthetic ratings). Outputs a 10-class probability distribution with a compact MobileNet backbone.
Aesthetic Scoring
Rates artistic appeal based on composition, color harmony, and visual balance. Trained on large-scale human preference data.
LAION Aesthetic v1
BundledLightweight linear probe on CLIP embeddings. Trained on LAION aesthetic ratings.
ViT-B/16 Aesthetic
Standalone ViT-B/16 fine-tuned on AVA dataset (250K human aesthetic ratings). Runs independently of CLIP.
Image Embedding
Turns photos into vectors for similarity clustering. Groups burst sequences and flags duplicates or near-duplicates.
Apple Vision FeaturePrint
BundledBuilt into macOS. No download required. Used for general-purpose scene similarity.
DINOv2 ViT-S/14
Self-supervised features from Meta's LVD-142M training. Used for visual similarity and scene structure.
CLIP ViT-B/32
Multimodal embeddings for grouping photos by content. Required by the LAION Aesthetic scorer.
Face Embedding
Builds face identity vectors for person grouping. Clusters photos by who appears in them.
EdgeFace-XS
Fastest option — lightweight 4 MB download. Good face grouping for most photos (LFW 99.73%). Best when speed is the priority.
EdgeFace-S
Good balance of speed and accuracy (LFW 99.82%, IJB-B 94.38%). Small download. Handles varied lighting well. Recommended balanced choice.
AdaFace IR-18
BundledStrong on low-quality and challenging face crops via adaptive margin (CVPR 2022). LFW 99.82%. Good mid-tier choice.
AdaFace IR-50
Top-tier accuracy (LFW 99.82%, IJB-B 95.67%). Excels on difficult poses and low-quality crops. Best when face grouping precision is critical.
AuraFace v1
Large ResNet-100 backbone with permissive Apache 2.0 license. Choose mainly for licensing requirements.
GhostFaceNets
SOTA 2025 lightweight face recognition model. High performance with minimal computational overhead.
Vision Language Model (VLM)
Reads photo content using natural language. Gives scene descriptions and quality reasoning that go beyond numerical scores.
Heuristic Estimate
BundledBuilt-in fallback using heuristic image analysis (sharpness, exposure, noise, faces). No download required. Replace with a real VLM for improved results.
SmolVLM2 256M
Smallest VLM — fastest inference with minimal memory. Basic scene recognition and quality commentary. Best for quick screening on constrained hardware.
SmolVLM2 2.2B
Full-size SmolVLM for scene description and quality reasoning. Slower than the 256M variant.
FastVLM 0.5B
Apple FastVLM with FastViTHD hybrid encoder. Tuned for on-device scene recognition.
FastVLM 1.5B
Largest VLM option in the list. Used for detailed scene descriptions and quality reasoning.
Image Classification
Tags photos with scene and object labels for filtering and organization. Uses Apple's Vision framework.
Apple Vision Classification
BundledBuilt-in macOS image classification using VNClassifyImageRequest. Fast, no download required. Provides scene and object tags for filtering.