Files
comfyui-workflows/optimized/R2V/minimax/continuum-tiled/README.md
T

6.7 KiB
Raw Blame History

MiniMax H3 Continuum — tiled upscale / multi-clip prompt study

This folder contains the supplied MiniMax H3 Continuum workflow with the DUMAS tiled latent upscale second pass. It is the working candidate for testing prompt direction and multi-clip construction toward a 20-second final video.

Source and status

  • Source: Unsaved_Workflow_5_1.json, supplied 2026-10-14.
  • Status: imported baseline; smoke validation pending on the live server.
  • Workflow: workflow.json
  • References: character-reference.png and scene-reference.png
  • Custom nodes: DUMAS H3 Continuum, DUMAS H3 Continuum Tiled, and the native MiniMax H3/Fearnworks/PlagueKind dependencies used by the graph.

What is fixed

These values are held constant while testing prompts and clip scaling:

  • Model: fastvideo_fasth3_8step_v2_pruned_int8_convrot.safetensors
  • Text encoder: qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors
  • Video VAE: minimax_h3_video_vae_int8_convrot.safetensors
  • Audio VAE: minimax_h3_audio_vae_fp32.safetensors
  • Main sampler: euler_ancestral
  • Main scheduler: simple
  • Main steps: 8
  • Main denoise: 1.0
  • Main seed: 12
  • Tiled second-pass sampler: sa_solver
  • Tiled second-pass scheduler: simple
  • Tiled second-pass steps: 2
  • Tiled second-pass denoise: 0.2
  • Tiled second-pass CFG: 1.0
  • Final output: 1920×1088
  • Latent upscale model: minimax_h3_latent_upscaler_3d_conv_v1_fp16.safetensors
  • Tile geometry: 1056×640, 96-pixel overlap, 32-pixel fade
  • Tiled mode: enabled through DUMAS H3 Continuum Second Pass

The imported graph starts at two 4-second Continuum chunks. The test matrix in tests.json increases the number of chunks through 20, 24, and 28 seconds, then tests a six-chunk, five-second-per-chunk configuration for the 30-second target. No sampler, scheduler, CFG, upscale or tile changes are included in this study.

Prompt strategy

The same character and scene references, seed, camera language, and visual direction are retained across the matrix. Prompt tests change only the structure and specificity of the action plan:

  1. Compact chronological action beats.
  2. Detailed chronological beats with explicit continuity.
  3. Detailed beats with camera direction and physical state tracking.
  4. Full 20-second plan with five linked 4-second beats.
  5. Longform 30-second plan with six linked 5-second beats.

Test procedure

  1. Run the 2-chunk smoke row first.
  2. Confirm the final output is routed through the DUMAS Second Pass with tiled_upscale=true and reaches 1920×1088.
  3. Repeat with the next prompt variant using the same 2 chunks.
  4. Keep the best prompt fixed, then test 3, 4, and 5 chunks.
  5. Continue through 24s and 28s; only then attempt the 30s five-second-chunk configuration.
  6. Stop if the server errors, OOMs, or runtime growth becomes disproportionate.
  7. Record each result beside the matrix with prompt hash, chunk count, runtime, output dimensions, and a motion/continuity verdict.

Test matrix and results

workflow.json is the supplied graph. workflow-spectrum-bypassed.json is an explicit structural bypass: the sampler, scheduler, second pass, and decode path connect directly to the LoRA/model output rather than relying only on Spectrum's enabled=false switch.

ID Workflow Prompt Chunks × seconds Target Status Result
CT-01 Spectrum graph Compact 2 × 4 8s Running Prompt 9c31d895-8ccf-4dd2-aefc-da13938f7418
CT-02 Spectrum graph Detailed continuity 2 × 4 8s Planned —
CT-03 Spectrum graph Cinematic camera 2 × 4 8s Planned —
CT-04 Spectrum graph Best smoke prompt 3 × 4 12s Planned —
CT-05 Spectrum graph Best smoke prompt 4 × 4 16s Planned —
CT-06 Spectrum graph Best smoke prompt 5 × 4 20s Planned —
CT-07 Spectrum graph Best smoke prompt 6 × 4 24s Planned —
CT-08 Spectrum graph Best smoke prompt 7 × 4 28s Planned —
CT-09 Spectrum graph Longform 30s 6 × 5 30s Planned —
CT-B01 Spectrum bypassed Compact 2 × 4 8s Planned —
CT-B02 Spectrum bypassed Detailed continuity 2 × 4 8s Planned —
CT-B03 Spectrum bypassed Cinematic camera 2 × 4 8s Planned —
CT-B04 Spectrum bypassed Best smoke prompt 3 × 4 12s Planned —
CT-B05 Spectrum bypassed Best smoke prompt 4 × 4 16s Planned —
CT-B06 Spectrum bypassed Best smoke prompt 5 × 4 20s Planned —
CT-B07 Spectrum bypassed Best smoke prompt 6 × 4 24s Planned —
CT-B08 Spectrum bypassed Best smoke prompt 7 × 4 28s Planned —
CT-B09 Spectrum bypassed Longform 30s 6 × 5 30s Planned —
CT-10 Spectrum graph Best smoke prompt 2 × 6 12s Planned —
CT-11 Spectrum graph Best smoke prompt 2 × 7 14s Planned —
CT-12 Spectrum graph Best smoke prompt 2 × 8 16s Planned —
CT-13 Spectrum graph Best smoke prompt 2 × 9 18s Planned —
CT-14 Spectrum graph Longform 30s 2 × 10 20s Planned —
CT-B10 Spectrum bypassed Best smoke prompt 2 × 6 12s Planned —
CT-B11 Spectrum bypassed Best smoke prompt 2 × 7 14s Planned —
CT-B12 Spectrum bypassed Best smoke prompt 2 × 8 16s Planned —
CT-B13 Spectrum bypassed Best smoke prompt 2 × 9 18s Planned —
CT-B14 Spectrum bypassed Longform 30s 2 × 10 20s Planned —

The CT-10–CT-14 sweep isolates individual chunk length: it holds the chunk count at two and increases chunk_seconds from 6 through 10. The bypass counterparts use the same settings. This shows whether longer individual clips are viable before combining them into 30-second projects.

The bypass series uses the identical seed, references, prompt text, model, samplers, scheduler, upscale settings, tile geometry, and chunk plan. Only the Spectrum path changes. Results should be compared in pairs: CT-01 vs CT-B01, CT-02 vs CT-B02, and so on.

Files

  • workflow.json — supplied ComfyUI API graph.
  • workflow-spectrum-bypassed.json — explicit Spectrum-bypass comparison graph.
  • prompt.txt — controlled base prompt for the study.
  • prompt-variants.json — exact smoke-test and 30-second prompt variants.
  • variables.json — immutable constants and allowed test variables.
  • tests.json — ordered test matrix.
  • character-reference.png, scene-reference.png — fixed references.
  • results/ — reserved for labelled outputs and metadata. Server output uses the matching continuum-tiled/<test-id>/ prefix.