Model page

Comfy-Org/z_image_turbo warn

downloads 6.1Mlikes 822license apache-2.0updated 2026-08-17

claims base: Tongyi-MAI/Z-Image-Turbo · chat template: not in config · view on Hugging Face ↗

Ingot findings

Static battery: 1 medium finding(s). Deep battery (behavioral differential, glitch-token pass) not yet run. Weights battery: embedding-norm scan over 151936 tokens (BF16, 2560-dim) found 0 undertrained candidates, 0 plain-ASCII. Lineage vs Tongyi-MAI/Z-Image-Turbo: consistent. Scanned 2026-08-20 (published from a community scan).

medium Repo ships executable Python (trust_remote_code)

The repository contains custom code files that run in-process when loaded with trust_remote_code=True. Pin the revision hash and review the code before loading.

How to fix

Review and pin the custom code; never float on `main` with trust_remote_code=True.

  1. Read every `.py` file in the repo before first load — this code runs in your process.
  2. Pin the revision: `from_pretrained(model_id, revision="<commit sha>", trust_remote_code=True)` so a later push can't swap the code under you.
  3. Prefer a version of the architecture already in `transformers` if one exists, which removes the remote-code requirement entirely.

info Embedding-norm glitch scan clean

No undertrained tokens found: every non-special token's embedding norm is above 0.3× the vocabulary median (1.126). The glitch-token data-corruption class has no candidate surface in this model.

How to fixruntime guardweight-level

Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.

  1. Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
  2. Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
  3. The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.

info Weights consistent with claimed parent Tongyi-MAI/Z-Image-Turbo

Mean cosine similarity of 64 sampled token-embedding rows against Tongyi-MAI/Z-Image-Turbo is 1.000 — the weights plausibly descend from the declared base (relation: unspecified).

How to fix

Fix or verify the `base_model` declaration so lineage checks can run.

  1. If you own the repo: correct the `base_model` field in the model card metadata to the real, public parent.
  2. If you don't: identify the true parent (config architecture + weight shapes narrow it fast) and re-scan with that lineage in mind.

Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.

Fingerprint

The durable weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.

vocabulary151,936 tokens
licenseapache-2.0
serializationsafetensors custom code
chat templatenone
claimed lineageTongyi-MAI/Z-Image-Turbo
lineage verifiedconsistent vs Tongyi-MAI/Z-Image-Turbo — embedding-row cosine 1.000
glitch-token surfaceclean no undertrained tokens
Full fingerprint
librarydiffusion-single-file
repo files11
revision08d044552790
HF snapshot6.1M downloads · 822 likes · updated 2026-08-17 · captured 2026-08-20
embedding tensormodel.embed_tokens.weight · BF16 · 151,936×2560
embedding normsmedian 1.1262 · mean 1.0974
lineage checkconsistent — cosine 1 over 64 sampled rows vs Tongyi-MAI/Z-Image-Turbo

Verdict badge

Ship the verdict in your README — it always shows the latest published analysis:

Ingot verdict: warn

[![Ingot scan](https://ingot.tools/api/v1/models/Comfy-Org/z_image_turbo/badge.svg)](https://ingot.tools/models/Comfy-Org/z_image_turbo)
Gate it in CI