Free webp to jpg
EN
Image MIME Reference
JPEG-AI-Sequence

JPEG AI Image Sequence

image/jais
VS

Radiance HDR

image/vnd.radiance
Radiance

A complete technical comparison of JPEG AI Image Sequence and Radiance HDR — covering compression, feature support, browser compatibility, magic bytes, and when to choose each format.

Equal browser support

Feature Support

Feature JPEG-AI-Sequence Radiance
Transparency (Alpha) Yes ✕ No
Animation Support Yes ✕ No
Progressive Loading Yes ✕ No
HDR Support Yes Yes
EXIF Metadata Yes ✕ No
ICC Color Profile Yes ✕ No
JPEG AI Image Sequence
image/jais
Extension
.jais
Container ISOBMFF / HEIF Image Sequence
Compression Lossy (Variational Autoencoder / Neural Network)
Algorithm
Deep Neural Network (Variational Autoencoder with Hyperpriors)
Color Depth 8-bit, 10-bit, 12-bit, 16-bit, Wide-gamut & HDR
Developed by Joint Photographic Experts Group (ISO/IEC JTC 1 / ITU-T)
Released 2025
Magic Bytes
.. .. .. .. 66 74 79 70 6A 61 69 73 (Size + ftypjais)
Full JPEG-AI-Sequence reference →
Radiance HDR
image/vnd.radiance
Extension
.hdr.pic.rgbe.xyze
Container Radiance Information Header
Compression Run-Length Encoding (RLE) / Uncompressed
Algorithm
Adaptive Run-Length Encoding (RLE)
Color Depth 32-bit (8-bit per channel RGB + 8-bit shared Exponent)
Developed by Greg Ward (Lawrence Berkeley National Laboratory)
Released 1989
Magic Bytes
23 3F 52 41 44 49 41 4E 43 45
Full Radiance reference →

Browser Support Comparison

Browser JPEG-AI-Sequence Radiance
Chrome Chrome
✕ ✕
Firefox Firefox
✕ ✕
Safari Safari
✕ ✕
Edge Edge
✕ ✕
IE IE (Legacy)
✕ ✕
JPEG-AI-Sequence

JPEG-AI-Sequence Strengths

  • Extends the state-of-the-art compression efficiency of JPEG AI to multi-frame image sequences and short animations
  • Allows machine vision algorithms to process temporal sequences (like surveillance bursts) directly in the compressed latent domain, saving immense computational power
  • Utilizes the robust, industry-standard ISOBMFF container for metadata, timing, and multi-track encapsulation
Limitations
  • Lacks native decoding support in current web browsers, operating systems, and video players
  • Decoding neural-network-compressed sequences requires significant compute overhead on hardware lacking dedicated AI accelerators (NPUs/GPUs)
  • Adoption is hindered by competition with established sequence formats like AVIF, HEVC (HEICS), and modern video codecs
Radiance

Radiance Strengths

  • Universally supported by almost every 3D modeling software, renderer, and game engine in existence
  • RGBE encoding offers a brilliant balance between High Dynamic Range capability and small file size (compared to 32-bit float OpenEXR)
  • Simple, easy-to-parse ASCII header followed by straightforward RLE binary data
Limitations
  • Does not support alpha transparency (no way to store an isolated light source with a transparent background)
  • The shared exponent architecture can occasionally introduce banding or color artifacts in extreme edge cases compared to true 16-bit/32-bit floating-point formats like OpenEXR
  • Zero native browser support for 2D viewing

When to choose which format

JPEG-AI-Sequence
Use JPEG-AI-Sequence when…
  • Machine Vision and AI Video/Burst Workflows
  • Cloud Storage Animation Optimization
  • Focal Stacks and Medical Volumetric Slices
  • Visual Surveillance Sequences
Radiance
Use Radiance when…
  • Image-Based Lighting (IBL)
  • 3D Environment Maps (HDRI Skydomes)
  • Lighting Simulation
  • VFX and CGI Rendering

More comparisons

JPEG-AI-Sequence vs ACES → Radiance vs ACES → JPEG-AI-Sequence vs APNG → Radiance vs APNG → JPEG-AI-Sequence vs AVCI → Radiance vs AVCI → JPEG-AI-Sequence vs AVCS → Radiance vs AVCS → JPEG-AI-Sequence vs AVIF → Radiance vs AVIF → All comparisons →
Share this comparison