Publish Models

cog push r8.im/owner/my-model

cog push

pip install git+https://github.com/replicate/cog-safe-push.git

cog-safe-push --test-hardware=gpu-l40s owner/my-model

model: owner/my-model
test_model: owner/my-model-test
test_hardware: gpu-l40s

predict:
  compare_outputs: false              # set false for stochastic models
  predict_timeout: 600
  test_cases:
    - inputs:
        prompt: "a serene mountain landscape"
      match_prompt: "a landscape photo of mountains"   # AI-judged via Claude
    - inputs:
        prompt: "a cat"
      match_url: "https://example.com/reference-cat.png"   # binary/image match
    - inputs:
        prompt: ""
      error_contains: "prompt cannot be empty"           # negative test
    - inputs:
        mode: "json"
      jq_query: '.confidence > 0.8 and .status == "success"'   # JSON output
    - inputs:
        prompt: "echo this"
      exact_string: "echo this"                          # exact string match
  fuzz:
    fixed_inputs:
      seed: 42
    disabled_inputs:
      - debug
    iterations: 10
    prompt: "Generate creative and diverse prompts"

train:                                  # if your model has a trainer
  destination: owner/my-model-trained
  destination_hardware: gpu-l40s
  train_timeout: 1800
  test_cases:
    - inputs:
        input_images: "https://.../training.zip"
        steps: 10

deployment:                             # auto-create or update on push
  name: my-model
  owner: owner
  hardware: gpu-l40s

parallel: 4
fast_push: false
ignore_schema_compatibility: false
official_model: owner/my-model         # for proxy/wrapper models, see below

# .github/workflows/push.yaml
name: Push to Replicate
on:
  workflow_dispatch:
    inputs:
      no_push:
        type: boolean
        default: false

jobs:
  push:
    runs-on: ubuntu-latest-4-cores       # builds need disk + cores
    steps:
      - uses: actions/checkout@v4
      - uses: jlumbroso/[email protected]
        with:
          tool-cache: false
          docker-images: false
      - uses: replicate/setup-cog@v2
        with:
          token: ${{ secrets.REPLICATE_API_TOKEN }}
      - run: pip install git+https://github.com/replicate/cog-safe-push.git
      - env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
          REPLICATE_API_TOKEN: ${{ secrets.REPLICATE_API_TOKEN }}
        run: |
          cog-safe-push -vv ${{ inputs.no_push && '--no-push' || '' }}

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}

# .github/workflows/ci.yaml
name: CI
on:
  pull_request: { branches: [main] }
  push: { branches: [main] }
  workflow_dispatch:
    inputs:
      models: { type: string, default: "all" }
      ignore_schema_checks: { type: boolean, default: false }
      cog_version: { type: string, default: "latest" }
      test_only: { type: boolean, default: false }

jobs:
  ci:
    uses: replicate/model-ci-template/.github/workflows/template.yaml@main
    with:
      trigger_type: ${{ github.event_name }}
      models: ${{ inputs.models || 'all' }}
      ignore_schema_checks: ${{ inputs.ignore_schema_checks || false }}
      cog_version: ${{ inputs.cog_version || 'latest' }}
      test_only: ${{ inputs.test_only || false }}
    secrets: inherit

jobs:
  prepare:
    runs-on: ubuntu-latest
    outputs:
      matrix: ${{ steps.set.outputs.matrix }}
    steps:
      - id: set
        run: |
          if [ "${{ inputs.models }}" = "all" ]; then
            echo 'matrix={"model":["schnell","dev","krea-dev"]}' >> "$GITHUB_OUTPUT"
          else
            list=$(echo "${{ inputs.models }}" | jq -Rc 'split(",")')
            echo "matrix={\"model\":$list}" >> "$GITHUB_OUTPUT"
          fi

  push:
    needs: prepare
    runs-on: ubuntu-latest-4-cores
    strategy:
      fail-fast: false
      matrix: ${{ fromJson(needs.prepare.outputs.matrix) }}
    steps:
      - uses: actions/checkout@v4
      - run: ./script/select.sh ${{ matrix.model }}     # produces cog.yaml from a template
      - run: cog-safe-push --config cog-safe-push-configs/${{ matrix.model }}.yaml -vv

./script/write-api-key                                              # bake API key into config
cog-safe-push --config cog-safe-push-configs/${MODEL}.yaml -vv

./script/delete-api-key                                             # strip the key
cog-safe-push --push-official-model --config cog-safe-push-configs/${MODEL}.yaml -vv

deployment:
  name: my-model
  owner: owner
  hardware: gpu-l40s

name: Hourly cog push check
on:
  schedule:
    - cron: "0 * * * *"
  workflow_dispatch:

jobs:
  check:
    runs-on: ubuntu-latest
    steps:
      - run: |
          # generate a tiny model with a unique uuid, push it, run a prediction
          # by digest, fail loudly if anything breaks.
          ./script/canary.sh