Model page

Comfy-Org/stable-diffusion-v1-5-archive pass

downloads 10.8Mlikes 115license creativeml-openrail-mupdated 2026-08-17

claims base: runwayml/stable-diffusion-v1-5 · chat template: not in config · view on Hugging Face ↗

Ingot findings

Static battery clean: safetensors weights, license declared, no template/tokenizer drift detected. Deep battery not yet run. Weights battery: embedding-norm scan over 49408 tokens (F16, 768-dim) found 215 undertrained candidates, 0 plain-ASCII. Lineage vs runwayml/stable-diffusion-v1-5: consistent. Scanned 2026-08-20 (published from a community scan).

low Undertrained tokens in vocabulary (non-ASCII tail)

Embedding-norm scan flagged 215 undertrained tokens (norm < 0.3× the vocabulary median), but 0 decode to plain-ASCII strings, so exposure in English-language pipelines is limited. Behavioral confirmation requires the GPU deep battery.

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 runwayml/stable-diffusion-v1-5

Mean cosine similarity of 64 sampled token-embedding rows against runwayml/stable-diffusion-v1-5 is 0.984 — 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.

vocabulary49,408 tokens
licensecreativeml-openrail-m
serializationsafetensors
chat templatenone
claimed lineagerunwayml/stable-diffusion-v1-5
lineage verifiedconsistent vs runwayml/stable-diffusion-v1-5 — embedding-row cosine 0.984
glitch-token surface215 undertrained candidates, 0 plain-ASCII
Full fingerprint
librarydiffusion-single-file
repo files5
revision9cfd06910195
HF snapshot10.8M downloads · 115 likes · updated 2026-08-17 · captured 2026-08-20
embedding tensorcond_stage_model.transformer.text_model.embeddings.token_embedding.weight · F16 · 49,408×768
embedding normsmedian 0.3886 · mean 0.3853
lineage checkconsistent — cosine 0.9844 over 64 sampled rows vs runwayml/stable-diffusion-v1-5

Verdict badge

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

Ingot verdict: pass

[![Ingot scan](https://ingot.tools/api/v1/models/Comfy-Org/stable-diffusion-v1-5-archive/badge.svg)](https://ingot.tools/models/Comfy-Org/stable-diffusion-v1-5-archive)
Gate it in CI