Skip to content
Model infoModelsSnapshot: 15 Oct 2026

ByteDance / DreamActor

DreamActor M1

Human-image animation with face, head and body guidance. Also offered through the native Jimeng motion-imitation API, producing 720p video at 24 fps.

availableClosed weightsVideo generation
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
9 of 23 specification fields collected
Output resolution720pSee specification notes below
Clip durationNot collectedAwaiting source review
Input billingSee ratesVolcengine Jimeng AI
Output billingSee ratesPublished units and conditions below

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
Context caching
Not collected
Parameters
Not collected
Architecture
Diffusion Transformer combining implicit face features, 3D head spheres and body skeletons with reference appearance guidance.Source for Architecture (opens in a new tab)
Knowledge cutoff
Not collected
Release date
Not collected
Languages
Not collected
Output resolutions
720pSource for Output resolutions (opens in a new tab)

Native Jimeng output; distinct from the research training recipe.

Published training data
500 hours of video, approximately balanced between full-body and half-body views, plus Nersemble for face quality.Source for Published training data (opens in a new tab)
Training hardware
8 H20 GPUs in the reported experimentsSource for Training hardware (opens in a new tab)
Published research configuration
Training clips: 25–121 frames, resized to 960 × 640 area while preserving aspect ratio. Inference segments: 73 frames, chained using the previous latent.Source for Published research configuration (opens in a new tab)

Research recipe, not a public API limit.

Frame rates (fps)
24 fps on native Volcengine JimengSource for Frame rates (fps) (opens in a new tab)

Access & pricing

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

API model ID
jimeng_dream_actor_m1_gen_video_cv
Access
Publicly documented hosted route. Activate the motion-imitation capability in a Volcengine account, authenticate and fund usage. No inference executed.
Regions
cn-north-1 (documented API signing region)
API endpoint URL
https://visual.volcengineapi.comSource for API endpoint URL (opens in a new tab)
Hosted API version
2022-08-31Source for Hosted API version (opens in a new tab)

Protocol version, not model release date.

Generation mode
CVSync2AsyncSubmitTask / CVSync2AsyncGetResultSource for Generation mode (opens in a new tab)
Authentication
Signed API requests; region cn-north-1 and service cv.Source for Authentication (opens in a new tab)

Authentication scope is not an independently verified data-residency guarantee.

Supported input workflows
Human driving video; reference image may show a human, anime character or common pet.Source for Supported input workflows (opens in a new tab)
Image input limits
JPEG/JPG/PNG; 480 × 480 through 1920 × 1080. Larger images are proportionally downscaled; file-size cap not established.Source for Image input limits (opens in a new tab)
Source video limits
MP4/MOV/WEBM; maximum 30 seconds; 200 × 200 through 2048 × 1440.Source for Source video limits (opens in a new tab)
Published request quota
One concurrent generationSource for Published request quota (opens in a new tab)
Result and task expiry
Generated video URL: one hour. Task may expire after 12 hours.Source for Result and task expiry (opens in a new tab)

These are retrieval lifetimes, not a data-deletion policy.

Content marking controls
Optional AIGC metadata through req_json.aigc_meta; inspect aigc_meta_tagged in the result.Source for Content marking controls (opens in a new tab)
Input media transport
Public image_url and video_url; optional callback_url.Source for Input media transport (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 15 Oct 2026
CategoryUsageRateUnit
Video generationGenerated video duration1CN¥0.50second

Rate conditions

  1. Native price per generated-video second, one concurrency. No conversion to USD, tokens or text questions. Duration rounding, applicable taxes and contract conditions are not established.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

API model ID
Not collected

Research project has no standalone API selector; use the separate native Jimeng endpoint.

Access
Original research project, without a standalone research API or checkpoint release. A separately documented native Jimeng hosted route is listed for this model.
Regions
Not collected

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

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

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.

Volcengine Jimeng AI

jimeng_dream_actor_m1_gen_video_cv
Not verified

No documented discounted prompt-cache contract. Task lifetime and latent reuse do not establish caching support.

How it works
Not collected

No documented discounted prompt-cache contract. Task lifetime and latent reuse do not establish caching support.

Minimum reusable input
Not collected

No documented discounted prompt-cache contract. Task lifetime and latent reuse do not establish caching support.

Lifetime & refresh
Not collected

No documented discounted prompt-cache contract. Task lifetime and latent reuse do not establish caching support.

How to enable it
Not collected

No documented discounted prompt-cache contract. Task lifetime and latent reuse do not establish caching support.

Usage fields
Not collected

No documented discounted prompt-cache contract. Task lifetime and latent reuse do not establish caching support.

Billing rules
Not collected

No documented discounted prompt-cache contract. Task lifetime and latent reuse do not establish caching support.

Limits & data boundaries
Not collected

No documented discounted prompt-cache contract. Task lifetime and latent reuse do not establish caching support.

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

Caching reviewed 15 Oct 2026

ByteDance research

Not verified

Session memory, retained media and model-internal latent buffers do not establish discounted prompt caching.

How it works
Not collected

Session memory, retained media and model-internal latent buffers do not establish discounted prompt caching.

Minimum reusable input
Not collected

Session memory, retained media and model-internal latent buffers do not establish discounted prompt caching.

Lifetime & refresh
Not collected

Session memory, retained media and model-internal latent buffers do not establish discounted prompt caching.

How to enable it
Not collected

Session memory, retained media and model-internal latent buffers do not establish discounted prompt caching.

Usage fields
Not collected

Session memory, retained media and model-internal latent buffers do not establish discounted prompt caching.

Billing rules
Not collected

Session memory, retained media and model-internal latent buffers do not establish discounted prompt caching.

Limits & data boundaries
Not collected

Session memory, retained media and model-internal latent buffers do not establish discounted prompt caching.

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

Caching reviewed 15 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

Inferred from the ByteDance model disclosures, official project repositories containing website assets rather than weights, and the reviewed ByteDance/ByteDance-Seed weight inventories with no matching checkpoint. No explicit weight-license declaration is asserted.

Classification evidence (opens in a new tab)

Lifecycle dates

Research paper first submitted2 Apr 2025Source (opens in a new tab)

Sources reviewed