Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Hyper3D / Deemos / DreamFace

DreamFace Normal Decoder

A custom trained decoder converts the shared texture latent into a facial normal map.

3D processing
restrictedClosed weights3D processing
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
6 of 21 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedDreamFace research publication
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected

Paper submission date is not a verified model release date.

Parameters
Not collected
Languages
Not collected
Context caching
Not collected
Architecture
Additional LDM decoder trained for normal-map translation.Source for Architecture (opens in a new tab)
Input modalities
Texture latentSource for Input modalities (opens in a new tab)
Output modalities
Normal mapSource for Output modalities (opens in a new tab)
Published training data
370 captured PBR texture tuples containing diffuse, specularity and normal maps.Source for Published training data (opens in a new tab)
PBR materials
SupportedSource for PBR materials (opens in a new tab)
Endpoint availability
Research edition; no exact public checkpoint download or current API selector verified.Source for Endpoint availability (opens in a new tab)
Usage metering
Not collected

No price for this research edition verified. Current ChatAvatar or Rodin charges are not inherited.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

DreamFace research publication

Provider source (opens in a new tab)
API model ID
Not collected

No callable selector for the exact research edition verified.

Access
Paper and public project description; original trained weights were not found in the reviewed official sources.
Regions
Not established

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

No deployed service contract assigned to this research component.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

DreamFace research publication

Not verified

No model-specific caching contract verified.

How it works
Not collected

No model-specific caching contract verified.

Minimum reusable input
Not collected

No model-specific caching contract verified.

Lifetime & refresh
Not collected

No model-specific caching contract verified.

How to enable it
Not collected

No model-specific caching contract verified.

Usage fields
Not collected

No model-specific caching contract verified.

Billing rules
Not collected

No model-specific caching contract verified.

Limits & data boundaries
Not collected

No model-specific caching contract verified.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Qualified unreleased-weight classification for the custom research components. The official project links a hosted demo, not original weights; reviewed Deemos/DEEMOSTECH model listings do not establish a release. Open Stable Diffusion and CLIP backbones do not establish release of these trained derivatives. Public availability may change.

Classification evidence (opens in a new tab)

Lifecycle dates

Research paper first submitted1 Apr 2023Source (opens in a new tab)

Sources reviewed