Add MiniMax R2V efficiency test plan

This commit is contained in:
Morpheus
2026-09-25 21:12:04 +00:00
parent 0f3fa0f4cf
commit b6a0f49cef
4 changed files with 69 additions and 0 deletions
+7
View File
@@ -0,0 +1,7 @@
# Reference-to-video workflows
The optimized R2V workflows use fixed prompt, reference, seed, resolution,
duration, and CFG variables for like-for-like comparisons. Efficiency nodes
are tested first on 3-second 480p clips before longer generations.
- [`minimax/`](minimax/) — MiniMax H3 R2V base and efficiency matrix
+48
View File
@@ -0,0 +1,48 @@
# MiniMax H3 — optimized reference-to-video
This is the first cleaned MiniMax H3 R2V evaluation workflow. It is derived
from the compact official MiniMax H3 int8 R2V graph and is kept separate from
the imported source workflows under `models/minimax/`.
## Fixed variables
- Reference media: supplied reference image/video from the workflow
- Prompt: replace per task, but keep fixed for each comparison batch
- Seed: keep fixed for each comparison batch
- Resolution: 864×480 (480p landscape)
- Duration: 3 seconds for the initial efficiency matrix
- CFG: **1.0**
- Model, text encoder, VAE, batch size, and denoise: fixed
## Base workflow
- `workflow.json` — derived ComfyUI web workflow
- Source control graph: `models/minimax/minimax-h3-int8-r2v/workflow.json`
- The imported source is not modified.
## Efficiency test matrix
The first two tests compare a normal control against the first compatible
memory-saving patch. All rows use the fixed variables above. The initial test
does not vary steps, sampler, or scheduler so that the efficiency difference
is isolated.
| ID | Memory path | Steps | Sampler | Scheduler | Duration | CFG | Runtime (s) | VRAM | Tested? | Valid? | Current Best |
|---|---|---:|---|---|---:|---:|---:|---:|---|---|---|
| MM-R2V-01 | Normal/control | 8 | workflow default | workflow default | 3 | 1.0 | — | — | No | — | No |
| MM-R2V-02 | MiniMaxH3MemoryEfficientSageAttentionPatch | 8 | workflow default | workflow default | 3 | 1.0 | — | — | No | — | No |
## Planned expansion
After these two tests:
1. Test other compatible memory nodes individually.
2. Test safe combinations of compatible nodes.
3. Sweep steps, sampler, and scheduler with the best efficiency path.
4. Run only the strongest 3-second configurations at 20 seconds.
5. Test reference-driven continuation/concatenation.
6. Compare latent upscale and RTX Video Super Resolution toward 1080p.
Every result must be saved as `results/<test-id>.*` with matching JSON
metadata containing the exact reference, prompt, seed, resolution, duration,
CFG, node settings, runtime, VRAM, validity, and visual verdict.
+13
View File
@@ -0,0 +1,13 @@
{
"reference_media": "workflow input",
"prompt": "workflow input",
"seed": "fixed per comparison batch",
"resolution": [864, 480],
"duration_seconds": 3,
"cfg": 1,
"model": "fixed by workflow",
"text_encoder": "fixed by workflow",
"vae": "fixed by workflow",
"batch_size": 1,
"denoise": "fixed by workflow"
}
File diff suppressed because one or more lines are too long