94 lines
5.4 KiB
Markdown
94 lines
5.4 KiB
Markdown
# MiniMax H3 sparse-attention latent-upscale study
|
||
|
||
This workflow variant is based on the supplied CSGlide H3 workflow. It uses:
|
||
|
||
- `fastvideo_fasth3_8step_v2_pruned_int8_convrot.safetensors`
|
||
- Block Sparse Attention with VSA selection
|
||
- Comfy Kitchen attention, MiniMax low-VRAM attention and chunked feed-forward
|
||
- 8-step Euler + beta initial generation
|
||
- MiniMax latent upscaling with tiled spatial splitting and latent refinement
|
||
- The supplied VAE, audio VAE, references, seed and one approximately 10-second clip
|
||
|
||
The workflow is preserved in `workflow-source.json`; `workflow.json` is the tracked test copy with the enhanced common prompt and corrected reference filenames.
|
||
|
||
## Fixed test input
|
||
|
||
- **References:** `references/Scene022.png` as `@image1`, `references/Char034_TurnaroundFull_001.png` as `@image2`
|
||
- **Clip:** 243 frames at 24 fps, approximately 10.125 seconds
|
||
- **Seed:** `317182692766673` for the initial sampler; keep it unchanged in every test
|
||
- **Initial sampler:** Euler, beta scheduler, 8 steps, denoise 1.0
|
||
- **Latent refinement:** SA solver, simple scheduler, 3 steps, denoise 0.2, CFG 1
|
||
- **Prompt:** `prompt.txt`; do not change it between tests
|
||
|
||
## Test matrix
|
||
|
||
Every test changes only the listed variables. Record runtime, peak VRAM, success/failure, output dimensions, visible seams, detail retention, anatomy, motion stability and audio output in the matching result JSON.
|
||
|
||
### Phase A — Upscale ceiling
|
||
|
||
| ID | Initial latent | Target latent | Tile | Purpose |
|
||
|---|---:|---:|---:|---|
|
||
| SLU-01 | 672×384 | 1344×768 | supplied baseline tile | Reproduce the supplied good result |
|
||
| SLU-02 | 672×384 | 1920×1080 | supplied baseline tile | Test the desired 1080p endpoint |
|
||
| SLU-03 | 672×384 | 1680×960 | supplied baseline tile | Intermediate fallback if 1080p fails or is too slow |
|
||
| SLU-04 | 672×384 | 1536×864 | supplied baseline tile | Practical quality/runtime fallback |
|
||
|
||
### Phase B — Tile size
|
||
|
||
Use the best successful target from Phase A and compare tile sizes while keeping overlap and all other settings fixed:
|
||
|
||
- SLU-05: 512×512 tiles
|
||
- SLU-06: 640×640 tiles
|
||
- SLU-07: 768×768 tiles
|
||
- SLU-08: 864×480-style wide tiles from the supplied workflow
|
||
- SLU-09: full-frame/no split if VRAM permits
|
||
|
||
For each tile, preserve 128-pixel spatial overlap where possible, then check seam visibility, runtime and peak VRAM.
|
||
|
||
### Phase C — Initial generation dimensions
|
||
|
||
Use the best target and tile combination:
|
||
|
||
- SLU-10: 672×384 supplied baseline
|
||
- SLU-11: 768×432
|
||
- SLU-12: 832×480 supplied alternate resolution node
|
||
- SLU-13: 960×544
|
||
- SLU-14: 1024×576 if the 8GB card remains stable
|
||
|
||
The initial aspect ratio must remain 16:9 and the same final target must be used for fair comparison.
|
||
|
||
### Phase D — Combined candidates
|
||
|
||
- SLU-15: best upscale ceiling + best tile + best initial dimensions
|
||
- SLU-16: quality-first combination, accepting a longer runtime if the visual improvement is clear
|
||
- SLU-17: practical production combination targeting a predictable sub-hour render
|
||
|
||
## First two runs
|
||
|
||
Run **SLU-01** and **SLU-02** first. SLU-01 validates the supplied configuration. SLU-02 directly tests whether 1080p is feasible on the RTX 3070. If SLU-02 exhausts VRAM, stalls or becomes impractically slow, stop that run and continue with SLU-03/04 rather than changing the prompt or seed.
|
||
|
||
## Evidence and verdict
|
||
|
||
The test is **VALIDATED** only when a configuration completes with a usable video and recorded measurements. A completed render with unacceptable seams, detail loss or motion instability is **PARTIAL**, not a success. Keep all result JSON and MP4 files under `results/`.
|
||
|
||
## Recorded valid runs
|
||
|
||
These are the valid runs recorded so far. Runtime is wall-clock generation time; the normalized figure is included because the output sizes differ.
|
||
|
||
| ID | Initial → output | Tile | Runtime | Runtime per output megapixel | Output | Review |
|
||
|---|---|---:|---:|---:|---:|---|
|
||
| SLU-01 | 672×384 → 1344×768 | 864×480 | 20m 09s | 19.51 min/Mpx | 1344×768 | Pending |
|
||
| SLU-02 | 672×384 → 1920×1088 | 864×480 | 32m 06s | 15.37 min/Mpx | 1920×1088 | Baseline |
|
||
| SLU-05 | 672×384 → 1920×1088 | 512×512 | 44m 48s | 21.45 min/Mpx | 1920×1088 | Valid; slower |
|
||
| SLU-06 | 672×384 → 1920×1088 | 640×640 | 26m 52s | 12.88 min/Mpx | 1920×1088 | **Reviewed best** |
|
||
| SLU-07 | 672×384 → 1920×1088 | 768×768 | 26m 01s | **12.45 min/Mpx** | 1920×1088 | Valid; visual comparison pending |
|
||
| SLU-08 | 672×384 → 1920×1088 | 864×480 | 31m 13s | 14.93 min/Mpx | 1920×1088 | Valid; visual comparison pending |
|
||
|
||
### Current best
|
||
|
||
**SLU-06 is the current best reviewed workflow**: it was judged better than the original 1080p baseline, with stable motion and no objectionable seams in the prior review, while cutting runtime from 32m 06s to 26m 52s. SLU-07 is the fastest measured result at 26m 01s and has the best normalized throughput, but it remains performance-only until its direct visual comparison is recorded. SLU-08 is valid but slower than SLU-06/07.
|
||
|
||
The next queued tests are **SLU-09** (full-frame/no split attempt at the same target; may fail on VRAM) and **SLU-11** (768×432 initial generation with the 768×768 tile). Static prompt, seed, references, model, samplers, schedulers, steps, denoise and final target remain unchanged.
|
||
|
||
The earlier tile submissions that produced 1024×1024 output are excluded from this table because their target-resolution override was not applied.
|