Offline Ambient-Controlled Latent Diffusion: Architecture, Telemetry, and On-Device Evaluation
On the map: Diffusion models → Diffusion foundations and sampling
Abstract (arXiv)
Most mobile image-generation applications are thin clients over cloud services, leaving outputs hard to audit. We present an Android latent-diffusion application that runs entirely on-device and is driven by the ambient-light sensor rather than a text prompt, keeping generation, telemetry, and storage local. The contribution is not a new diffusion method but the surrounding measurement workflow: each output is bound to the sensor reading, runtime path, and seed that produced it, giving a per-artifact audit trail for offline analysis. On a single Samsung foldable, one fixed capture of 373 artifacts shows the controller's log-lux input positively associated with output luminance (Pearson r=0.532, 95% CI [0.455, 0.601]), confirming the ambient dependency survives denoising and VAE decoding, while the latent UNet/VAE pipeline runs at 552--1334,ms mean latency across three quality tiers under the Android Neural Networks API (NNAPI).
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 5 of its 22 references that are in the map. First posted on arXiv 4 Aug 2026.
Builds on
5 of 22 references.
Closest ancestors · 2
Same direction, newest first
- 2020Denoising Diffusion Implicit Models6 Oct
- 2020Denoising Diffusion Probabilistic Models19 Jun
Other references · 3
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
- 2022A Theory of Factors Affecting Continuous Experimentation (FACE)cited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices
- 2023Squeezing Large-Scale Diffusion Models for Mobile
- 2026EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation
- 2026SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
- 2025MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices
- 2025High-resolution efficient image generation from WiFi CSI using a pretrained latent diffusion model
- 2024Hardware-Friendly Diffusion Models with Fixed-Size Reusable Structures for On-Device Image Generation
- 2023MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices