Video · multimodal-generation · text-to-image

Show-o

showlab

Runtime source is vendored in-tree; current WorldFoundry wrapper supports t2i image generation.

Runner verifiedUnified environmentshow-o

Build your run

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

worldfoundry.pipeline
Taskmultimodal-generation
Environmentworldfoundry-unified-cu128
DeviceCUDA 11.3
worldfoundry-eval evaluate \
  --mode model \
  --model-id show-o \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/show-o \
  --metric artifact_count \
  --json
01

Compatibility & versions

Manifest-backed recipe

Integration
runtime ported
Runner evidence
verified
Environment
worldfoundry-unified-cu128
Python
3.10
CUDA
CUDA 11.3
PyTorch
torch
Source revision
Checkpoint revision
c2c6f548c00444432a97bc8fbbce7b2fd73fc9b5
Runtime profile
show-o
Pipeline binding
show-o
Runner
worldfoundry.pipeline
Pipeline target
worldfoundry.pipelines.component_pipelines:ShowOPipeline
Backend stage
in_tree_runtime
Runtime status
in_tree_show_o_runtime_ported_t2i_ready
Driver status
compatible_with_downgraded_torch
Environment kind
Unified 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 show-o
Package constraints 18
  • torch
  • torchvision
  • accelerate
  • datasets
  • diffusers
  • einops
  • fairscale
  • huggingface-hub
  • numpy
  • omegaconf
  • open-clip-torch
  • opencv-python
  • pillow
  • safetensors
  • sentencepiece
  • timm
  • tokenizers
  • transformers
Conda packages 3
  • python
  • pip
  • ffmpeg
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 show-o --check-local --json
showlab/show-o
Revision
c2c6f548c00444432a97bc8fbbce7b2fd73fc9b5
License
mit
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 show-o \
  --model-runner worldfoundry:pipeline \
  --model-manifest-dir worldfoundry/data/models/catalog \
  --requests-path tmp/requests.jsonl \
  --output-dir tmp/model_eval/show-o \
  --metric artifact_count \
  --json

Input contract

FieldRecorded contract
imageOptional
modet2i
promptRequired

Artifact contract

Artifact kindFilename / path
generated_imageshow_o.png
05

Evidence & sources

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

Integration
runtime ported
Runner evidence
verified
Native demo evidence
Not recorded
Validation imports
torch, diffusers, transformers, open_clip
Recipe provenance
worldfoundry/data/models/catalog/video/show-o.yamlGitHubhttps://github.com/showlab/Show-o