ComfyUI Node
Eric Krea2 Sweep Plan
A ComfyUI node in Eric/Krea2 with 37 inputs and 1 output.
Eric Krea2 Sweep Plan
- sweep
◄modegrid►
◄stage_scopes1►
◄samplerseuler, res_2m, res_2s, deis_3m, abnorsett_3m, abnorsett_4m, lawson4_4s, etdrk4_4s, er_sde, rk6_7s, lcm, lcm_hybrid, lcm_hybrid2►
◄schedulerslinear, balanced, karras, beta57, beta, bong_tangent, exponential, linear_quadratic, simple, 4mp-lcm, Candidate 1, Claude-1, Claude-8mp, EXP1, EXP2, EXP3, EXP4, EXP5, EXP6, Kreamania3-2stage-4.5mp, OPT-AB412, OPT-DEIS12, kreamania3-2stage-8mp►
◄pair_lockfalse►
◄steps►
◄windows►
◄etas►
◄noise_types►
◄cfgs►
◄shift_modes►
◄mus►
◄combos_file►
◄combos_json►
◄seed_policyfixed►
◄seeds►
◄quick_screenfalse►
◄screen_megapixels1.00►
◄score_metricstrue►
◄sort_byplan_order►
◄tile_px448►
◄max_combos64►
◄output_folder►
◄hybrid_steps►
◄megapixels►
◄lora_modenone►
◄lora_files►
◄lora_strengths►
◄lora_target1►
◄include_baselinetrue►
◄keep_panel_stackfalse►
◄prompts►
◄sigma_profiles►
◄lora_triggersappend►
◄enabledtrue►
◄sweep_presetcustom►
◄preset_notes►
CategoryEric/Krea2
Inputs (37)
| Name | Type | Default | Description |
|---|---|---|---|
| mode | COMBO | grid | 2 options: grid, combos |
| stage_scope | COMBO | s1 | Which stage(s) the swept keys apply to. all_stages sets the same value on s1+s2+s3 together (NOT a per-stage cross product). Workflow intent: perfect S1 first (quick_screen), then sweep s2/s3 refinement on the short list. |
| samplersopt | STRING | euler, res_2m, res_2s, deis_3m, abnorsett_3m, abnorsett_4m, lawson4_4s, etdrk4_4s, er_sde, rk6_7s, lcm, lcm_hybrid, lcm_hybrid2 | Comma/newline-separated. Allowed: euler, res_2m, res_2s, deis_3m, abnorsett_3m, abnorsett_4m, lawson4_4s, etdrk4_4s, er_sde, rk6_7s, lcm, lcm_hybrid, lcm_hybrid2. Pre-populated with all of them - delete what you don't want. Blank = not swept. Crossed with hybrid_steps, only the hybrid samplers expand per split value; other samplers keep one cell (inert-split dedupe). |
| schedulersopt | STRING | linear, balanced, karras, beta57, beta, bong_tangent, exponential, linear_quadratic, simple, 4mp-lcm, Candidate 1, Claude-1, Claude-8mp, EXP1, EXP2, EXP3, EXP4, EXP5, EXP6, Kreamania3-2stage-4.5mp, OPT-AB412, OPT-DEIS12, kreamania3-2stage-8mp | Built-in schedules AND saved sigma-shape ★ preset names, mixed freely: each entry is tried as a schedule (linear, balanced, karras, beta57, beta, bong_tangent, exponential, linear_quadratic, simple) first, then as a sigmas preset (applied as a full profile for that cell); unknown names are SKIPPED with a console warning instead of aborting. Pre-populated with everything available - delete what you don't want. Blank = not swept. |
| pair_lockopt | BOOLEAN | false | ON: zip samplers+schedulers line-by-line into fixed pairs (lists must be equal length) - for testing known recipes. OFF: full cross product. |
| stepsopt | STRING | e.g. '8, 10, 12'. Maps to <stage>_steps. | |
| windowsopt | STRING | Refine windows 'start-end', e.g. '5-12, 6-12, 7-12'. Maps to <stage>_start_step/<stage>_end_step. Pair with matching steps or leave steps blank and window within the panel's step count. | |
| etasopt | STRING | e.g. '0, 0.3, 1.0' -> <stage>_eta. | |
| noise_typesopt | STRING | Allowed: white, low_freq, high_freq, pink. lcm-family samplers force white (per the 2026-07-23 rainbow fix); those cells are auto-coerced and labeled, never silently divergent. | |
| cfgsopt | STRING | e.g. '1.0, 1.5, 2.0' -> <stage>_cfg. Diagnostic for RAW-drifted fine tunes: tolerance of cfg>1 tracks how far training eroded the turbo distillation. | |
| shift_modesopt | STRING | distilled_shift values to sweep: fixed / resolution / manual. | |
| musopt | STRING | shift mu values for the scoped stage(s), e.g. '1.15, 2.1, 3.0'. Forces distilled_shift=manual on those cells (unless shift_modes is also swept, which then wins the cross). | |
| combos_fileopt | STRING | combos mode: path to a JSON file with the runs - either a JSON array of override objects, {"combos": [...]}, or JSON-lines. Takes precedence over combos_json below. Keeps sweep campaigns as versionable files. | |
| combos_jsonopt | STRING | combos mode: one JSON object per line using Ultra V2 widget keys (same keys as presets / PNG recipes), e.g. {"s2_sampler": "lcm_hybrid", "s2_steps": 12, "s2_start_step": 6} Copy-paste directly from a preset or a stamped PNG. | |
| seed_policyopt | COMBO | fixed | fixed: every cell uses the Ultra panel seed (required for fair comparison). seeds_axis: 'seeds' below becomes one more grid axis. |
| seedsopt | STRING | seeds_axis values, e.g. '1, 2, 3'. | |
| quick_screenopt | BOOLEAN | false | Force S1-only at screen_megapixels for every cell (upscale_to_stage2/3 = 0). Cheap wide screening; re-run the short list full-pipeline after. |
| screen_megapixelsopt | FLOAT | 1.000.25–8 | — |
| score_metricsopt | BOOLEAN | true | Compute technical metrics per cell (CPU, ms): Laplacian + Tenengrad sharpness, wavelet noise sigma, flat-region chroma variance (splotch detector), clip fraction. Scores annotate + can sort the sheet; they never hide a cell. |
| sort_byopt | COMBO | plan_order | Contact-sheet order. Metrics sort best-first; time_s fastest-first. Manifest keeps plan order + this ordering separately. |
| tile_pxopt | INT | 448128–1024 | — |
| max_combosopt | INT | 641–4096 | Hard cap. Over-cap plans REFUSE with an axis-size breakdown (no silent truncation). |
| output_folderopt | STRING | Where sweep folders are created. Blank = ComfyUI output/sweeps. An absolute path is used as-is; a relative path is created under the ComfyUI output directory. | |
| hybrid_stepsopt | STRING | Sweep the hybrids' handoff in EXACT lcm steps, e.g. '3, 4, 5, 6' -> <stage>_hybrid_steps for the scoped stage(s). Only lcm_hybrid / lcm_hybrid2 read it - pair with a hybrid in the samplers axis (or on the panel); inert cells are deduped. Values clamp inside each stage's window so both halves always run; sweeping values past window-1 collapses to the same cell. | |
| megapixelsopt | STRING | Sweep s1_megapixels, e.g. '0.5, 1.0, 2.0, 4.5'. Always targets Stage 1 regardless of stage_scope (stage 2/3 sizes chain from it via the upscale factors). Mixed cell sizes are fine: metrics and the contact sheet use each cell's native output; the IMAGE batch output center-pads smaller cells to the largest. quick_screen does NOT override a swept megapixels value. Note: resolution changes the noise grid, so composition shifts with size even at a fixed seed - that is part of what you are measuring. | |
| lora_modeopt | COMBO | none | bakeoff: each LoRA in lora_files at each lora_strengths value - by default the swept LoRA runs ALONE (panel stack replaced) so every style is measured against the bare checkpoint; keep_panel_stack layers it on top instead. strength_ladder: keep the panel-declared stack, step ONLY the lora_target entry through lora_strengths. Sweep-injected entries are ephemeral (fused per cell, cleaned per cell). |
| lora_filesopt | STRING | bakeoff: one LoRA per line - a name from the loras folder (same resolution as the LoRA Stack node) or a full path. | |
| lora_strengthsopt | STRING | e.g. '0.6, 0.8, 1.0'. One value drives all three stage weights (weight_s1=s2=s3). bakeoff: every file at every value; ladder: the target entry's values. | |
| lora_targetopt | STRING | 1 | strength_ladder: which panel-stack entry to vary - 1-based index, or a name substring (matches lora_name/filename). |
| include_baselineopt | BOOLEAN | true | Add one reference cell: bakeoff = no LoRA at all (or the panel stack alone when keep_panel_stack is ON); ladder = the panel stack exactly as declared. |
| keep_panel_stackopt | BOOLEAN | false | bakeoff only: append the swept LoRA ON TOP of the panel stack instead of replacing it. |
| promptsopt | STRING | One prompt per line = a prompt axis (slowest axis, so the sheet and CSV read in prompt-major blocks). Each prompt cell re-encodes (prompt_conditioning is cleared; ~seconds/cell). Metric comparisons are only meaningful WITHIN a prompt block. | |
| sigma_profilesopt | STRING | Comma/newline list of saved sigma-shape preset NAMES (the ★ presets of the Eric Krea2 Sigmas node). Each cell rebuilds the full bundle from that preset and it OVERRIDES any wired sigmas node for that cell. Blank = not swept. | |
| lora_triggersopt | COMBO | append | bakeoff: merge each cell's swept-LoRA trigger words into that cell's prompt (from the LoRA Stack node's cached trigger database; first-seen files may do one network lookup, non-fatal on failure). Only sweep-injected entries contribute - baseline and ladder cells are untouched. A cell whose prompt text changes re-encodes automatically. Effective prompt + triggers are recorded in the cell's metadata. |
| enabledopt | BOOLEAN | true | Off = the node outputs nothing and Ultra V2 runs a normal single generation - leave the sweep wired in the workflow and toggle it. |
| sweep_presetopt | COMBO | custom | Named sweep plans from sweep_presets.json. Selecting one WRITES its values into this panel (so you can see exactly what will run); editing any field flips back to 'custom'. Save the panel as a preset with the ★ button. Headless/API: the named preset applies fully. Ask Claude to author experiment presets. |
| preset_notesopt | STRING | One or two sentences: what this sweep preset is FOR and what it does. Saved and loaded with the ★ preset - so future-you remembers why it exists. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| sweep | KREA2_SWEEP | — |