Official repository for Testing-model checkpoints, evaluated on AI-generated image detection and segmentation tasks. To download the latest checkpoint directly to your local workspace
Independent publisher
Truong
KhangTruong
Natural language processing
Compare the published evidence
This profile connects the 4 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Image segmentation.
Reported licenses: apache-2.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Official repository for gap-efficient-sam checkpoints, evaluated on AI-generated image detection and segmentation tasks. To download the latest checkpoint directly to your local workspace
Datasets
Pre-computed High-Dimensional Forensic Latents for ultra-fast Diffusion-Diff forensics training. - imgid (string): Image identifier. - label (int64): Class label (0: authentic, 1: fully synthetic, 2: tampered/inpainted). - zhighdim (binary): Pre-computed 84-channel fp16 latent tensor bytes. - mask (binary): Ground-truth binary manipulation mask encoded as PNG bytes. - channels (int64): Total channel count (84). - latenth (int64): Latent height (64). - latentw (int64): Latent width (64).
Pre-computed High-Dimensional Forensic Latents for ultra-fast Diffusion-Diff forensics training. - imgid (string): Image identifier. - label (int64): Class label (0: authentic, 1: fully synthetic, 2: tampered/inpainted). - zhighdim (binary): Pre-computed 256-channel fp16 latent tensor bytes. - mask (binary): Ground-truth binary manipulation mask encoded as PNG bytes. - channels (int64): Total channel count (256). - latenth (int64): Latent height (32). - latentw (int64): Latent width (32).