# ISIS v2 Cinematic Shot Sequence Baseline Workflow Graph

Generated: 2026-08-02T19:12:18.284Z Checklist: `MXA-0470` (ISIS2-00668) Asset
Family: `cinematic-shot-sequence` Phase: Phase 4 | Milestone: M3 Launch
(2026-07-27 to 2026-10-30)

## Objective

Provide a deterministic baseline workflow graph for cinematic-shot-sequence
generation with locked sampler/model defaults and reproducible shot framing,
motion intent, and video assembly.

## Deterministic Defaults

| Setting           | Value                        |
| ----------------- | ---------------------------- |
| `checkpointModel` | `sd_xl_base_1.0.safetensors` |
| `seed`            | `2026112807`                 |
| `width`           | `1920`                       |
| `height`          | `1080`                       |
| `steps`           | `28`                         |
| `cfgScale`        | `6`                          |
| `samplerName`     | `dpmpp_2m_sde`               |
| `scheduler`       | `karras`                     |
| `denoise`         | `1`                          |
| `batchSize`       | `1`                          |
| `durationSeconds` | `4`                          |
| `frameRate`       | `24`                         |
| `outputFormat`    | `mp4`                        |
| `outputChannels`  | `3`                          |

## Input Contract

| Input               | Type    | Required | Default                                                                                              |
| ------------------- | ------- | -------- | ---------------------------------------------------------------------------------------------------- |
| `sequence_id`       | string  | yes      | `SEQ01_SH010`                                                                                        |
| `scene_description` | string  | yes      | `Protagonist exits a moving tram and tracks a target through crowded evening traffic.`               |
| `shot_goal`         | string  | yes      | `Establish intent, lock subject trajectory, and preserve eyeline continuity through the move.`       |
| `camera_setup`      | enum    | yes      | `tracking`                                                                                           |
| `camera_motion`     | enum    | yes      | `dolly-in`                                                                                           |
| `lens_mm`           | integer | yes      | `35`                                                                                                 |
| `aspect_ratio`      | enum    | yes      | `2.39:1`                                                                                             |
| `duration_seconds`  | float   | yes      | `4`                                                                                                  |
| `frame_rate`        | integer | yes      | `24`                                                                                                 |
| `style_preset`      | enum    | yes      | `cinematic-live-action`                                                                              |
| `continuity_notes`  | string  | yes      | `Preserve subject eyeline, camera axis, and lighting continuity from previous shot.`                 |
| `negative_prompt`   | string  | no       | `blurry, low resolution, bad anatomy, extra limbs, duplicated face, text, watermark, jpeg artifacts` |
| `seed`              | integer | yes      | `2026112807`                                                                                         |
| `width`             | integer | yes      | `1920`                                                                                               |
| `height`            | integer | yes      | `1080`                                                                                               |
| `steps`             | integer | yes      | `28`                                                                                                 |
| `cfg_scale`         | float   | yes      | `6`                                                                                                  |

## Graph Nodes

| Node ID | Class                    | Role                  | Output Count |
| ------- | ------------------------ | --------------------- | ------------ |
| `n1`    | `CheckpointLoaderSimple` | model-load            | 3            |
| `n2`    | `CLIPTextEncode`         | positive-conditioning | 1            |
| `n3`    | `CLIPTextEncode`         | negative-conditioning | 1            |
| `n4`    | `EmptyLatentImage`       | latent-init           | 1            |
| `n5`    | `KSampler`               | latent-sample         | 1            |
| `n6`    | `VAEDecode`              | image-decode          | 1            |
| `n7`    | `SaveVideo`              | artifact-output       | 0            |

## Graph Edges

| Edge ID | From   | To                |
| ------- | ------ | ----------------- |
| `e1`    | `n1:0` | `n5.model`        |
| `e2`    | `n1:1` | `n2.clip`         |
| `e3`    | `n1:1` | `n3.clip`         |
| `e4`    | `n1:2` | `n6.vae`          |
| `e5`    | `n2:0` | `n5.positive`     |
| `e6`    | `n3:0` | `n5.negative`     |
| `e7`    | `n4:0` | `n5.latent_image` |
| `e8`    | `n5:0` | `n6.samples`      |
| `e9`    | `n6:0` | `n7.frames`       |

## Topological Node Order

`n1` -> `n2` -> `n3` -> `n4` -> `n5` -> `n6` -> `n7`

## Research Alignment

| Workflow                            | Path                                                                  | Node Classes                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
| ----------------------------------- | --------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Visual Concept Explainer Generator  | `libs/isis/workflows/src/workflows/video/concept-explainer.json`      | `ADE_AnimateDiffLoaderGen1`, `ADE_MultivalDynamic`, `ADE_StandardUniformContextOptions`, `CLIPTextEncode`, `CheckpointLoaderSimple`, `ColorEnhancement`, `EmptyLatentImage`, `ImageScaleBy`, `ImageUpscaleWithModel`, `KSampler`, `LoraLoader`, `LoraLoaderModelOnly`, `RIFE VFI`, `TemporalConsistencyProcessor`, `UpscaleModelLoader`, `VAEDecode`, `VHS_VideoCombine`                                                                                                                |
| AnimateDiff with ControlNet         | `libs/isis/workflows/src/workflows/video/animatediff-controlnet.json` | `ADE_AnimateDiffLoaderGen1`, `ADE_MultivalDynamic`, `ADE_StandardUniformContextOptions`, `CLIPTextEncode`, `CheckpointLoaderSimple`, `ControlNetApply`, `ControlNetLoader`, `EmptyLatentImage`, `ImageScaleBy`, `ImageUpscaleWithModel`, `IsisLoadImageList`, `KSampler`, `LoopProcessor`, `LoraLoaderModelOnly`, `RIFE VFI`, `SaveImage`, `TemporalConsistencyProcessor`, `UpscaleModelLoader`, `VAEDecode`, `VHS_VideoCombine`, `{{control_mode_configs[control_mode].preprocessor}}` |
| Educational Lecture Scene Generator | `libs/isis/workflows/src/workflows/video/lecture-scene.json`          | `ADE_AnimateDiffLoaderGen1`, `ADE_MultivalDynamic`, `ADE_StandardUniformContextOptions`, `CLIPTextEncode`, `CheckpointLoaderSimple`, `EmptyLatentImage`, `ImageScaleBy`, `ImageUpscaleWithModel`, `KSampler`, `LoraLoader`, `LoraLoaderModelOnly`, `RIFE VFI`, `TemporalConsistencyProcessor`, `UpscaleModelLoader`, `VAEDecode`, `VHS_VideoCombine`                                                                                                                                    |

## Acceptance Criteria

- Graph is acyclic and topologically sortable.
- All deterministic defaults are explicitly set (seed, sampler, scheduler,
  checkpoint).
- Node class inventory covers baseline generation path from prompt conditioning
  to persisted video output.
- Output contract aligns to MXA-0469 cinematic-shot-sequence required output
  classes.

## Traceability

- Checklist item: `MXA-0470`
- Ticket key: `ISIS2-00668`
- Source references:
  - `docs/domains/isis/remediation-v2/ISIS_REMEDIATION_V2_TICKETS.json`
  - `docs/domains/isis/remediation-v2/ISIS_V2_CINEMATIC_SHOT_SEQUENCE_REQUIREMENTS_BRIEF.json`
  - `libs/isis/workflows/src/workflows/video/concept-explainer.json`
  - `libs/isis/workflows/src/workflows/video/animatediff-controlnet.json`
  - `libs/isis/workflows/src/workflows/video/lecture-scene.json`
  - `docs/domains/isis/remediation-v2/ISIS_V2_CONTROL_TAXONOMY.json`
  - `docs/domains/isis/remediation-v2/ISIS_V2_OUTPUT_PACKAGE_TAXONOMY.json`
  - `ISIS_TODOS_2.md`
