# ISIS v2 VFX Element Pack Baseline Workflow Graph

Generated: 2026-08-02T18:33:38.822Z Checklist: `MXA-0416` (ISIS2-00614) Asset
Family: `vfx-element-pack` Phase: Phase 4 | Milestone: M3 Launch (2026-07-27 to
2026-10-30)

## Objective

Provide a deterministic baseline text-to-image workflow graph for
vfx-element-pack generation with locked sampler/model defaults and reproducible
compositing-ready effect element output topology.

## Deterministic Defaults

| Setting           | Value                        |
| ----------------- | ---------------------------- |
| `checkpointModel` | `sd_xl_base_1.0.safetensors` |
| `seed`            | `2026111601`                 |
| `width`           | `1920`                       |
| `height`          | `1080`                       |
| `steps`           | `34`                         |
| `cfgScale`        | `5.6`                        |
| `samplerName`     | `dpmpp_2m_sde`               |
| `scheduler`       | `karras`                     |
| `denoise`         | `1`                          |
| `batchSize`       | `1`                          |
| `outputFormat`    | `png`                        |
| `outputChannels`  | `4`                          |

## Input Contract

| Input                          | Type    | Required | Default                                                                                                                                                          |
| ------------------------------ | ------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `effect_type`                  | enum    | yes      | `smoke-plume`                                                                                                                                                    |
| `style_profile`                | enum    | yes      | `photoreal-cinematic`                                                                                                                                            |
| `shot_context`                 | enum    | yes      | `mid-shot`                                                                                                                                                       |
| `lighting_interaction_profile` | enum    | yes      | `backlit-volumetric`                                                                                                                                             |
| `medium_profile`               | enum    | yes      | `dense-smoke`                                                                                                                                                    |
| `motion_profile`               | enum    | yes      | `directional-sweep`                                                                                                                                              |
| `element_density_profile`      | enum    | yes      | `balanced`                                                                                                                                                       |
| `turbulence_profile`           | enum    | yes      | `medium`                                                                                                                                                         |
| `emission_color_profile`       | enum    | yes      | `warm-ember`                                                                                                                                                     |
| `alpha_background_mode`        | enum    | yes      | `transparent`                                                                                                                                                    |
| `render_resolution_class`      | enum    | yes      | `1080p`                                                                                                                                                          |
| `camera_lens_profile`          | enum    | yes      | `standard-35mm`                                                                                                                                                  |
| `compositing_intent`           | string  | yes      | `layered foreground/mid/background separable with clean alpha edges and stable luminance for comp stack blending`                                                |
| `negative_prompt`              | string  | no       | `matte fringing, edge halos, chroma spill, clipping, posterized gradients, noisy compression artifacts, duplicate ghost trails, text, watermark, jpeg artifacts` |
| `seed`                         | integer | yes      | `2026111601`                                                                                                                                                     |
| `width`                        | integer | yes      | `1920`                                                                                                                                                           |
| `height`                       | integer | yes      | `1080`                                                                                                                                                           |
| `steps`                        | integer | yes      | `34`                                                                                                                                                             |
| `cfg_scale`                    | float   | yes      | `5.6`                                                                                                                                                            |

## 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`    | `SaveImage`              | 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.images`       |

## Topological Node Order

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

## Research Alignment

| Workflow                       | Path                                                                  | Node Classes                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
| ------------------------------ | --------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| HDRI Environment Map Generator | `libs/isis/workflows/src/workflows/texture/environment-map.json`      | `CLIPTextEncode`, `CheckpointLoaderSimple`, `EmptyLatentImage`, `EnvironmentMapFormatter`, `FreeU_V2`, `HDRProcessor`, `KSampler`, `LatentUpscaleBy`, `SaveImage`, `VAEDecode`                                                                                                                                                                                                                                                                                                          |
| 3D Texture Generator           | `libs/isis/workflows/src/workflows/texture/3d-texture.json`           | `CLIPTextEncode`, `CheckpointLoaderSimple`, `EmptyLatentImage`, `FreeU_V2`, `KSampler`, `LatentUpscaleBy`, `MakeSeamless`, `NormalMapGenerator`, `SaveImage`, `VAEDecode`                                                                                                                                                                                                                                                                                                               |
| 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}}` |

## 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 image output.
- Output contract aligns to MXA-0415 required output classes.

## Traceability

- Checklist item: `MXA-0416`
- Ticket key: `ISIS2-00614`
- Source references:
  - `docs/domains/isis/remediation-v2/ISIS_REMEDIATION_V2_TICKETS.json`
  - `docs/domains/isis/remediation-v2/ISIS_V2_VFX_ELEMENT_PACK_REQUIREMENTS_BRIEF.json`
  - `libs/isis/workflows/src/workflows/texture/environment-map.json`
  - `libs/isis/workflows/src/workflows/texture/3d-texture.json`
  - `libs/isis/workflows/src/workflows/video/animatediff-controlnet.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`
