Eve library

ISIS v2 Environment Concept Art Control-Conditioned Workflow Graph

Guide

Revision 1

On this page

Generated: 2026-08-02T14:59:26.686Z Checklist: MXA-0130 (ISIS2-00328) Asset Family: environment-concept-art Phase: Phase 4 | Milestone: M3 Launch (2026-07-27 to 2026-10-30)

Objective#

Define a control-conditioned workflow graph for environment concept art that supports pose, depth, segmentation, normal, canny, and lineart constraints while preserving deterministic defaults.

Deterministic Defaults#

Setting Value
checkpointModel sd_xl_base_1.0.safetensors
seed 2026100204
width 1536
height 896
steps 34
cfgScale 6.3
samplerName dpmpp_2m_sde
scheduler karras
denoise 1
poseControlModel control_v11p_sd15_openpose.safetensors
depthControlModel control_v11f1p_sd15_depth.safetensors
segmentationControlModel control_v11p_sd15_seg.safetensors
normalControlModel control_v11p_sd15_normalbae.safetensors
cannyControlModel control_v11p_sd15_canny.safetensors
lineartControlModel control_v11p_sd15_lineart.safetensors
poseStrength 0.7
depthStrength 0.65
segmentationStrength 0.6
normalStrength 0.66
cannyStrength 0.64
lineartStrength 0.62
batchSize 1
outputFormat png
outputChannels 4

Input Contract#

Input Type Required Default
pose_map image no n/a
depth_map image no n/a
segmentation_map image no n/a
normal_map image no n/a
canny_map image no n/a
lineart_map image no n/a
use_pose_control boolean yes true
use_depth_control boolean yes true
use_segmentation_control boolean yes false
use_normal_control boolean yes false
use_canny_control boolean yes false
use_lineart_control boolean yes false
pose_strength float yes 0.7
depth_strength float yes 0.65
segmentation_strength float yes 0.6
normal_strength float yes 0.66
canny_strength float yes 0.64
lineart_strength float yes 0.62
environment_type enum yes natural-landscape
biome_context enum yes coastal-megacity
architectural_style enum yes neo-futurist
composition_profile enum yes layered-depth
camera_framing enum yes 35mm-balanced
time_of_day enum yes sunset-golden
weather_system enum yes mist
lighting_mood enum yes soft-diffuse
color_palette_profile string yes slate blue haze, warm practical amber, moss green mids, low-sat neutrals
style_preset enum yes stylized
negative_prompt string no blurry, low resolution, muddy textures, warped perspective, tiling artifacts, duplicated structures, text, watermark, jpeg artifacts
seed integer yes 2026100204
width integer yes 1536
height integer yes 896
steps integer yes 34
cfg_scale float yes 6.3

Graph Nodes#

Node ID Class Role Output Count
n1 LoadImage pose-control-input 2
n2 LoadImage depth-control-input 2
n3 LoadImage segmentation-control-input 2
n4 CheckpointLoaderSimple model-load 3
n5 ControlNetLoader pose-control-load 1
n6 ControlNetLoader depth-control-load 1
n7 ControlNetLoader segmentation-control-load 1
n8 CLIPTextEncode positive-conditioning 1
n9 CLIPTextEncode negative-conditioning 1
n10 ControlNetApply pose-control-apply 1
n11 ControlNetApply depth-control-apply 1
n12 ControlNetApply segmentation-control-apply 1
n13 EmptyLatentImage latent-init 1
n14 KSampler latent-sample 1
n15 VAEDecode image-decode 1
n16 SaveImage artifact-output 0
n17 LoadImage normal-control-input 2
n18 LoadImage canny-control-input 2
n19 LoadImage lineart-control-input 2
n20 ControlNetLoader normal-control-load 1
n21 ControlNetLoader canny-control-load 1
n22 ControlNetLoader lineart-control-load 1
n23 ControlNetApply normal-control-apply 1
n24 ControlNetApply canny-control-apply 1
n25 ControlNetApply lineart-control-apply 1

Graph Edges#

Edge ID From To
e1 n4:0 n14.model
e2 n4:1 n8.clip
e3 n4:1 n9.clip
e4 n4:2 n15.vae
e5 n8:0 n10.conditioning
e6 n5:0 n10.control_net
e7 n1:0 n10.image
e8 n10:0 n11.conditioning
e9 n6:0 n11.control_net
e10 n2:0 n11.image
e11 n11:0 n12.conditioning
e12 n7:0 n12.control_net
e13 n3:0 n12.image
e14 n12:0 n23.conditioning
e15 n9:0 n14.negative
e16 n13:0 n14.latent_image
e17 n14:0 n15.samples
e18 n15:0 n16.images
e19 n20:0 n23.control_net
e20 n17:0 n23.image
e21 n23:0 n24.conditioning
e22 n21:0 n24.control_net
e23 n18:0 n24.image
e24 n24:0 n25.conditioning
e25 n22:0 n25.control_net
e26 n19:0 n25.image
e27 n25:0 n14.positive

Topological Node Order#

n1 -> n13 -> n17 -> n18 -> n19 -> n2 -> n20 -> n21 -> n22 -> n3 -> n4 -> n5 -> n6 -> n7 -> n8 -> n10 -> n11 -> n12 -> n23 -> n24 -> n25 -> n9 -> n14 -> n15 -> n16

Research Alignment#

Workflow Path Control Nodes
AnimateDiff with ControlNet libs/isis/workflows/src/workflows/video/animatediff-controlnet.json 2
HDRI Environment Map Generator libs/isis/workflows/src/workflows/texture/environment-map.json 0
3D Texture Generator libs/isis/workflows/src/workflows/texture/3d-texture.json 0

Acceptance Criteria#

  • Graph is acyclic and topologically sortable.
  • Pose, depth, segmentation, normal, canny, and lineart control paths are explicitly represented through ControlNet loaders and apply nodes.
  • At least one control mode can be enabled per run without breaking deterministic sampler/model defaults.
  • Output contract aligns to MXA-0127 required output classes.
  • Environment structure, camera framing, and palette fields are first-class required inputs for controlled generation.

Traceability#

  • Checklist item: MXA-0130
  • Ticket key: ISIS2-00328
  • Source references:
    • docs/domains/isis/remediation-v2/ISIS_REMEDIATION_V2_TICKETS.json
    • docs/domains/isis/remediation-v2/ISIS_V2_ENVIRONMENT_CONCEPT_ART_REQUIREMENTS_BRIEF.json
    • docs/domains/isis/remediation-v2/ISIS_V2_ENVIRONMENT_CONCEPT_ART_BASELINE_WORKFLOW_GRAPH.json
    • docs/domains/isis/remediation-v2/ISIS_V2_ENVIRONMENT_CONCEPT_ART_IMAGE_CONDITIONED_WORKFLOW_GRAPH.json
    • libs/isis/workflows/src/workflows/video/animatediff-controlnet.json
    • libs/isis/workflows/src/workflows/texture/environment-map.json
    • libs/isis/workflows/src/workflows/texture/3d-texture.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