SourceScore

Verified claim · AI-ML · 100% confidence

Latent Diffusion Models (LDM) introduced in paper: High-Resolution Image Synthesis with Latent Diffusion Models (Rombach et al., 2021).

Last verified 2026-05-16 · Methodology veritas-v0.1 · 1aacbf0bf9248dc7

Structured fields

Subject
Latent Diffusion Models (LDM)
Predicate
introduced_in_paper
Object
High-Resolution Image Synthesis with Latent Diffusion Models (Rombach et al., 2021)
Confidence
100%
Tags
latent-diffusion · ldm · image-generation · stable-diffusion-backbone · foundational · 2021

Sources (2)

  1. [1] preprint · arXiv (Rombach, Blattmann, Lorenz, Esser, Ommer) · 2021-12-20

    High-Resolution Image Synthesis with Latent Diffusion Models
    We apply diffusion models in the latent space of powerful pretrained autoencoders. … we achieve a near-optimal point between complexity reduction and detail preservation, greatly boosting visual fidelity.
  2. [2] github release · CompVis (Heidelberg) · 2021-12-20

    CompVis/latent-diffusion — official implementation

Cite this claim

Ready-to-paste citation (Markdown / plain text):

Latent Diffusion Models (LDM) introduced in paper: High-Resolution Image Synthesis with Latent Diffusion Models (Rombach et al., 2021). — SourceScore Claim 1aacbf0bf9248dc7 (verified 2026-05-16). https://sourcescore.org/api/v1/claims/1aacbf0bf9248dc7.json

Embed this claim

Drop this iframe into any blog post, docs page, or knowledge base. The widget renders the signed claim + primary source + click-through to this canonical page. CC-BY 4.0; attribution included.

<iframe src="https://sourcescore.org/embed/claim/1aacbf0bf9248dc7/" width="100%" height="360" frameborder="0" loading="lazy" title="Latent Diffusion Models (LDM) introduced in paper: High-Resolution Image Synthesis with Latent Diffusion Models (Rombach et al., 2021)."></iframe>

Preview: open in new tab

Related claims

Other verified claims sharing tags with this one — useful for LLM retrieval graphs and citation discovery.

Use this claim in your code

Fetch this signed envelope from your application. The response includes the verbatim excerpt, primary source URLs, and an HMAC-SHA256 signature you can verify locally for audit trails.

cURL

curl https://sourcescore.org/api/v1/claims/1aacbf0bf9248dc7.json

JavaScript / TypeScript

const r = await fetch("https://sourcescore.org/api/v1/claims/1aacbf0bf9248dc7.json"); const envelope = await r.json(); console.log(envelope.claim.statement); // "Latent Diffusion Models (LDM) introduced in paper: High-Resolution Image Synthesis with Latent Diffusion Models (Rombach et al., 2021)."

Python

import httpx r = httpx.get("https://sourcescore.org/api/v1/claims/1aacbf0bf9248dc7.json") envelope = r.json() print(envelope["claim"]["statement"]) # "Latent Diffusion Models (LDM) introduced in paper: High-Resolution Image Synthesis with Latent Diffusion Models (Rombach et al., 2021)."

LangChain (retrieve-then-cite)

from langchain_core.tools import tool import httpx @tool def get_latent_diffusion_models_ldm_fact() -> dict: """Fetch the verified SourceScore claim for Latent Diffusion Models (LDM).""" r = httpx.get("https://sourcescore.org/api/v1/claims/1aacbf0bf9248dc7.json") return r.json()