Skip to content

Parity

imagehub adds a model only after it reproduces the original implementation. This section shows what was measured, how, and where the claim stops.

123 / 123checkpoints with recorded end-to-end evidence

0largest recorded pixel difference

CPU · fp32where parity is claimed

80models in the side-by-side gallery

The method

For each checkpoint, in this order:

  1. Strict load. Every published tensor is loaded; any missing, extra or mismatched name or shape fails the model.
  2. Components. The tokenizer, text encoders, transformer or U-Net, VAE and scheduler are each compared with the reference on the same inputs.
  3. End to end. A full generation from the same initial noise is compared with the reference: final latents and final pixels.
  4. Tolerance. The accepted difference is written down before the run; for most models it is exactly zero.

The recorded reference is the model's implementation in diffusers 0.40.0 and transformers 5.18.0, or its official implementation where those libraries do not cover it. Measurements use PyTorch 2.14.1.

Reading the results

Page Contents
Gallery The reference image and the imagehub image side by side, with a slider
Results One row per checkpoint with steps, size and the largest recorded difference
Full validation record Method, tolerances, device tests, limits and the bugs found

Where the claim stops

Parity has a scope

  • It holds on CPU in float32 against the stated library versions.
  • MPS and CUDA runs are smoke tests, not parity.
  • There is no float16 or bfloat16 parity claim.
  • It is not a quality benchmark: no FID or CLIP score was run.
  • There is no safety checker or invisible watermark; the reference was run without one.

The complete list is in the limits.