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.pngandscene-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:
3for the adjusted EasyCache + clear-VRAM flows (the original control workflows remain at2) - 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:
- Compact chronological action beats.
- Detailed chronological beats with explicit continuity.
- Detailed beats with camera direction and physical state tracking.
- Full 20-second plan with five linked 4-second beats.
- Longform 30-second plan with six linked 5-second beats.
Test procedure
- Run the 2-chunk smoke row first.
- Confirm the final output is routed through the DUMAS Second Pass with
tiled_upscale=trueand reaches 1920×1088. - Repeat with the next prompt variant using the same 2 chunks.
- Keep the best prompt fixed, then test 3, 4, and 5 chunks.
- Continue through 24s and 28s; only then attempt the 30s five-second-chunk configuration.
- Stop if the server errors, OOMs, or runtime growth becomes disproportionate.
- 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 configured | Completed | 17m 49.959s render; expected 4.0s output, 1920×1088, 96 frames |
| CT-02 | Spectrum + EasyCache + clear VRAM | Detailed continuity | 2 × 4 | 8s | Planned | — |
| CT-03 | Spectrum + EasyCache + clear VRAM | Cinematic camera | 2 × 4 | 8s | Planned | — |
| CT-04 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 3 × 4 | 12s | Planned | — |
| CT-05 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 4 × 4 | 16s | Planned | — |
| CT-06 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 5 × 4 | 20s | Planned | — |
| CT-07 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 6 × 4 | 24s | Planned | — |
| CT-08 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 7 × 4 | 28s | Planned | — |
| CT-09 | Spectrum + EasyCache + clear VRAM | Longform 30s | 6 × 5 | 30s | Planned | — |
| CT-B01 | Spectrum bypassed | Compact | 2 × 4 | 8s configured | Completed | 16m 42.576s render; 4.0s output, 1920×1088, 24 fps, 96 frames; 1/2 logical chunks emitted |
| CT-B02 | Bypassed + EasyCache + clear VRAM | Detailed continuity | 2 × 4 | 8s | Planned | — |
| CT-B03 | Bypassed + EasyCache + clear VRAM | Cinematic camera | 2 × 4 | 8s | Planned | — |
| CT-B04 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 3 × 4 | 12s | Planned | — |
| CT-B05 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 4 × 4 | 16s | Planned | — |
| CT-B06 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 5 × 4 | 20s | Planned | — |
| CT-B07 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 6 × 4 | 24s | Planned | — |
| CT-B08 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 7 × 4 | 28s | Planned | — |
| CT-B09 | Bypassed + EasyCache + clear VRAM | Longform 30s | 6 × 5 | 30s | Planned | — |
| CT-10 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 6 | 12s | Planned | — |
| CT-11 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 7 | 14s | Planned | — |
| CT-12 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 8 | 16s | Planned | — |
| CT-13 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 9 | 18s | Planned | — |
| CT-14 | Spectrum + EasyCache + clear VRAM | Longform 30s | 2 × 10 | 20s | Planned | — |
| CT-B10 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 6 | 12s | Planned | — |
| CT-B11 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 7 | 14s | Planned | — |
| CT-B12 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 8 | 16s | Planned | — |
| CT-B13 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 9 | 18s | Planned | — |
| CT-B14 | Bypassed + EasyCache + clear VRAM | 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.
Runtime planning
The latest observed reference is 18 minutes for one 4-second chunk. Until more measurements are available, the monitoring estimate is:
expected minutes = 18 × (total generated seconds ÷ 4) + 5-minute buffer
Examples:
| Generated duration | Estimated render | Monitoring window |
|---|---|---|
| 4s | 18m | 23m |
| 5s | 22.5m | 28m |
| 8s | 36m | 41m |
| 20s | 90m | 95m |
| 30s | 135m | 140m |
These are planning windows, not performance guarantees. Each completed test must replace its estimate with the measured runtime and the model should be recalibrated if multi-clip scaling is not approximately linear.
CT-01 and CT-B01 remain the two no-cache controls. Every later row adds
EasyCache with reuse threshold 0.3, active from 20% to 90% of sampling, and
verbose logging disabled. Those rows also pass the completed DUMAS second-pass
video output through AusBoss Free Memory 🆎 immediately before decode. It
clears ComfyUI/CUDA caches while preserving the video-sample wire. The
clear-VRAM node is deliberately after tiled upscale, so it cannot evict the
model before the second pass has finished.
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.
CT-B01 measured relationship
CT-B01 was accepted with dumas-continuum-character.png and
dumas-continuum-scene.png, and configured for 2 logical chunks × 4.0s =
8.0s. The review-mode execution completed only the first physical chunk, so
node 382 emitted a 4.0s MP4 (96 frames at 24 fps) while logical chunk 2
remained pending. The measured render duration was 1,002.576s (16m
42.576s), and the output metadata reported 1920×1088 at 24 fps.
Files
workflow.json— supplied ComfyUI API graph.workflow-spectrum-bypassed.json— explicit Spectrum-bypass comparison graph.workflow-easy-cache.json— Spectrum graph with EasyCache enabled.workflow-spectrum-bypassed-easy-cache.json— bypass graph with EasyCache enabled.workflow-easy-cache-clear-vram.json— Spectrum graph with EasyCache and pass-through VRAM cleanup after the DUMAS second pass.workflow-spectrum-bypassed-easy-cache-clear-vram.json— bypass graph with EasyCache and pass-through VRAM cleanup after the DUMAS second pass.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 matchingcontinuum-tiled/<test-id>/prefix.