Eve library
ISIS v2 NPC Crowd Variation Pack Control-Conditioned Workflow Graph
Guide
Revision 1
On this page
Generated: 2026-08-02T17:39:31.281Z Checklist: MXA-0094 (ISIS2-00292) Asset
Family: npc-crowd-variation-pack Phase: Phase 4 | Milestone: M3 Launch
(2026-07-27 to 2026-10-30)
Objective#
Define a control-conditioned npc-crowd-variation-pack workflow graph that
supports pose/depth/segmentation/normal/canny/lineart constraints while
preserving deterministic generation defaults and crowd-layout readability for
production review.
Deterministic Defaults#
Setting
Value
checkpointModel
sd_xl_base_1.0.safetensors
seed
2026090204
width
1920
height
1080
steps
34
cfgScale
6.2
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
0.74
depthStrength
0.68
segmentationStrength
0.62
normalStrength
0.7
cannyStrength
0.62
lineartStrength
0.64
batchSize
1
outputFormat
png
outputChannels
4
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
0.74
depth_strength
float
yes
0.68
segmentation_strength
float
yes
0.62
normal_strength
float
yes
0.7
canny_strength
float
yes
0.62
lineart_strength
float
yes
0.64
character_archetype
enum
yes
hero
style_preset
enum
yes
stylized
crowd_role_profile
enum
yes
civilians-mixed
crowd_activity_profile
enum
yes
market-flow
crowd_layout_pattern
enum
yes
staggered-depth-lanes
wardrobe_variation_profile
enum
yes
neutral-market-tones
environment_context
enum
yes
market-square
camera_framing
enum
yes
wide-crowd
seed
integer
yes
2026090204
width
integer
yes
1920
height
integer
yes
1080
steps
integer
yes
34
cfg_scale
float
yes
6.2
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
ControlNetLoader
normal-control-load
1
n19
ControlNetApply
normal-control-apply
1
n20
LoadImage
canny-control-input
2
n21
ControlNetLoader
canny-control-load
1
n22
ControlNetApply
canny-control-apply
1
n23
LoadImage
lineart-control-input
2
n24
ControlNetLoader
lineart-control-load
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
n25:0
n14.positive
e15
n9:0
n14.negative
e16
n13:0
n14.latent_image
e17
n14:0
n15.samples
e18
n15:0
n16.images
e19
n12:0
n19.conditioning
e20
n18:0
n19.control_net
e21
n17:0
n19.image
e22
n19:0
n22.conditioning
e23
n21:0
n22.control_net
e24
n20:0
n22.image
e25
n22:0
n25.conditioning
e26
n24:0
n25.control_net
e27
n23:0
n25.image
Topological Node Order#
n1 -> n13 -> n17 -> n18 -> n2 -> n20 -> n21 -> n23 -> n24 ->
n3 -> n4 -> n5 -> n6 -> n7 -> n8 -> n10 -> n11 -> n12 -> n19
-> n22 -> n25 -> n9 -> n14 -> n15 -> n16
Research Alignment#
Workflow
Path
Control Nodes
AnimateDiff with ControlNet
libs/isis/workflows/src/workflows/video/animatediff-controlnet.json
2
Stable Zero123 Multi-View Generator
libs/isis/workflows/src/workflows/3d/stable-zero123.json
0
Consistent Character Generator
libs/isis/workflows/src/workflows/avatar/consistent-character.json
0
Acceptance Criteria#
Graph is acyclic and topologically sortable.
Pose/depth/segmentation/normal/canny/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-0091 required output classes.
Traceability#
Checklist item: MXA-0094
Ticket key: ISIS2-00292
Source references:
docs/domains/isis/remediation-v2/ISIS_REMEDIATION_V2_TICKETS.json
docs/domains/isis/remediation-v2/ISIS_V2_NPC_CROWD_VARIATION_PACK_REQUIREMENTS_BRIEF.json
docs/domains/isis/remediation-v2/ISIS_V2_NPC_CROWD_VARIATION_PACK_BASELINE_WORKFLOW_GRAPH.json
docs/domains/isis/remediation-v2/ISIS_V2_NPC_CROWD_VARIATION_PACK_IMAGE_CONDITIONED_WORKFLOW_GRAPH.json
libs/isis/workflows/src/workflows/video/animatediff-controlnet.json
libs/isis/workflows/src/workflows/3d/stable-zero123.json
libs/isis/workflows/src/workflows/avatar/consistent-character.json
docs/domains/isis/remediation-v2/ISIS_V2_CONTROL_TAXONOMY.json
docs/domains/isis/remediation-v2/ISIS_V2_WORKFLOW_AUTHORING_GUIDE.json
ISIS_TODOS_2.md