WorldFoundry
English中文

Video · text-to-image · image-to-image · text-to-video · video-to-video · reference-to-video · reference-video-to-video

Bernini-R 1.3B

ByteDance

Official renderer inference is vendored in-tree; no external Bernini checkout is used.

IntegratedDedicated environmentPinned sourcebernini-r-1.3b

Build your run

Choose a recorded variant, then copy the exact setup or inspection command.

worldfoundry.pipeline
Tasktext-to-image
Environmentworldfoundry-bernini-cu124
DeviceCUDA 12.4
worldfoundry-eval evaluate \
  --mode model \
  --model-id bernini-r-1.3b \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/bernini-r-1.3b \
  --metric artifact_count \
  --json
01

Compatibility & versions

Manifest-backed recipe

Integration
integrated
Runner evidence
pending gpu validation
Environment
worldfoundry-bernini-cu124
Python
3.11
CUDA
CUDA 12.4
PyTorch
torch==2.5.1+cu124
Source revision
82d573e9a553dccb1405dde4cb0f26466f9df6c5
Checkpoint revision
ff4c5d4d2d31365c2ffeb30e9753065ee18f58ce
Runtime profile
bernini-r-1.3b
Pipeline binding
bernini-r-1.3b
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.bernini.pipeline_bernini:BerniniWorldFoundryPipeline
Backend stage
official_in_tree_runtime
Runtime status
checkpoint_assets_pending_not_runnable_until_staged
Driver status
compatible
Environment kind
Dedicated environment
02

Install environment

The environment resolver reads the recorded profile and chooses the unified or dedicated environment shown here.

bash scripts/setup/model_env_install.sh --model bernini-r-1.3b
Package constraints 19
  • torch==2.5.1+cu124
  • torchvision==0.20.1+cu124
  • diffusers==0.35.2
  • accelerate==0.34.2
  • transformers==4.57.3
  • huggingface-hub
  • flash-attn==2.8.3
  • safetensors
  • einops
  • numpy
  • Pillow
  • tqdm
  • ftfy
  • decord
  • imageio
  • imageio-ffmpeg
  • scipy
  • loguru
  • veomni @ git+https://github.com/ByteDance-Seed/VeOmni.git@v0.1.10
Conda packages 5
  • python=3.11
  • pip
  • ffmpeg
  • ninja
  • cuda-nvcc
03

Checkpoints & assets

Run the local check before allocating compute. Gated, private, and license fields below come directly from the checkpoint manifest.

worldfoundry-eval zoo model-download --model-id bernini-r-1.3b --check-local --json
ByteDance/Bernini-R-1.3B-Diffusers
Revision
—
License
apache-2.0
Gated
—
Private
—
ByteDance/Bernini-R-1.3B-Diffusers
Revision
ff4c5d4d2d31365c2ffeb30e9753065ee18f58ce
License
—
Gated
—
Private
—
04

Launch & outputs

The generated command uses the shared evaluation boundary and writes durable result manifests and artifacts.

worldfoundry-eval evaluate \
  --mode model \
  --model-id bernini-r-1.3b \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/bernini-r-1.3b \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
promptRequired
imageRequired
imagesRequired
videoRequired
task_typet2i, i2i, t2v, v2v, r2v, rv2v

Artifact contract

Artifact kindFilename / path
generated_image—
generated_video—
generated_videobernini-r-1.3b.mp4
05

Evidence & sources

Catalog integration, native-demo parity, and runner parity are independent records.

Integration
integrated
Runner evidence
pending gpu validation
Native demo evidence
Not recorded
Validation imports
torch, torchvision, diffusers, transformers, huggingface_hub, accelerate, flash_attn, veomni, decord, imageio, loguru
Recipe provenance
worldfoundry/data/models/catalog/video/bernini-r-1.3b.yamlProjecthttps://bernini-ai.github.io/Paperhttps://arxiv.org/abs/2605.22344GitHub82d573e9a553dccb1405dde4cb0f26466f9df6c5Hugging Facehttps://huggingface.co/ByteDance/Bernini-R-1.3B-Diffusers