genblaze-luma
Luma Dream Machine (Ray-2) video provider adapter for genblaze — text-to-video AI pipelines with SHA-256 provenance manifests on every render.
genblaze-luma wraps Luma Labs' Dream Machine API (Ray-2, Ray-Flash-2) as a genblaze provider. Compose Luma video generations into multi-step AI pipelines, persist outputs to Backblaze B2 or any S3-compatible store, and emit a tamper-evident provenance manifest for every run.
Why genblaze-luma
- Luma Ray-2, unified API — same
PipelineAPI as Sora, Veo, Runway, Flux. - Provenance by default — SHA-256-verified manifest with prompt, model, and params on every render.
- Production-ready — timeouts, retries, progress streaming, moderation hooks, step caching.
- Composable — chain Luma outputs into downstream FFmpeg steps or AV compositors.
- Durable storage — plug
genblaze-s3in for Backblaze B2 / AWS S3 / R2 / MinIO persistence.
Models
| Model | Notes |
|---|---|
ray-2 |
Latest, highest-quality Dream Machine |
ray-flash-2 |
Faster and lower-cost variant |
Install
pip install genblaze-luma
Registers the luma provider via entry points; genblaze-core discovers it automatically.
Quickstart — Ray-2 text-to-video
pip install genblaze-core genblaze-luma
export LUMAAI_API_KEY="..."
from genblaze_core import Modality, Pipeline
from genblaze_luma import LumaProvider
run, manifest = (
Pipeline("luma-demo")
.step(LumaProvider(), model="ray-2",
prompt="A slow-motion shot of ocean waves crashing against volcanic rocks at golden hour, cinematic",
modality=Modality.VIDEO, aspect_ratio="16:9")
.run(timeout=300)
)
print(run.steps[0].assets[0].url, manifest.canonical_hash)
Persist to Backblaze B2
from genblaze_core import KeyStrategy, ObjectStorageSink
from genblaze_s3 import S3StorageBackend
storage = ObjectStorageSink(
S3StorageBackend.for_backblaze("my-bucket"),
key_strategy=KeyStrategy.HIERARCHICAL,
)
# pass sink=storage to .run(…)
Backblaze B2 is the recommended default sink for large AI-generated video.
Credentials
| Env var | Where to get it |
|---|---|
LUMAAI_API_KEY |
https://lumalabs.ai/dream-machine/api |
Documentation
- Main repo: https://github.com/backblaze-labs/genblaze
- Example:
luma_video_pipeline.py
Related packages
genblaze-core— the pipeline SDKgenblaze-s3— durable storage on Backblaze B2 and other S3-compatible backends- Other video providers:
genblaze-openai(Sora) ·genblaze-google(Veo) ·genblaze-runway(Gen-4) ·genblaze-decart(Lucy)
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for genblaze-luma 0.3.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| genblaze_luma-0.3.2.tar.gz | 9.7 kB | With provenance | Details for genblaze_luma-0.3.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| genblaze_luma-0.3.2-py3-none-any.whl | Python 3 | none | any | Details for genblaze_luma-0.3.2-py3-none-any.whl |
Total release size: 17.7 kB
Release files / genblaze_luma-0.3.2.tar.gz
| Download URL | genblaze_luma-0.3.2.tar.gz |
|---|---|
| Size | 9.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a1f0b8c7b7bc55be4de2095e407be7e677028e31d1da888492610ccac2a08b76
|
|
BLAKE2b-256 checksum How to use checksums |
ad719ec01e10b9a7c58c2eca8401d50e45a3c2ae5105a1a41087ebeae489bc09
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.13
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 22, 2026.
Transparency logRelease files / genblaze_luma-0.3.2-py3-none-any.whl
| Download URL | genblaze_luma-0.3.2-py3-none-any.whl |
|---|---|
| Size | 8.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3fac4414d83a483f36d36f92285a2ae5b7bc5f1792c18f71404b2af2139e9fcb
|
|
BLAKE2b-256 checksum How to use checksums |
0d61776eef811ebaf7caf6b1e4eefd2a3aeacf192be1b4d6cdce52d573d2ab15
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.13
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 22, 2026.
Transparency logSecurity for genblaze-luma 0.3.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for genblaze_luma-0.3.2.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 22, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
