Promote high resolution MiniMax baseline
This commit is contained in:
@@ -26,7 +26,7 @@ substitute another configuration.
|
||||
- `workflow.json` — ComfyUI web workflow derived from the source graph
|
||||
- `api-workflow.json` — validated API graph for the current Turbo baseline
|
||||
- `reference.png` — fixed character reference
|
||||
- `prompt.txt` — fixed haunted-room investigation prompt
|
||||
- `prompt.txt` — fixed bright park-and-robins prompt
|
||||
- `variables.json` — fixed comparison variables
|
||||
- `results/` — labelled outputs and matching JSON metadata
|
||||
|
||||
@@ -34,11 +34,10 @@ substitute another configuration.
|
||||
|
||||
**MM-R2V-58** remains the 3-second production baseline: Turbo LoRA enabled, 8
|
||||
steps, Res Multistep sampler, simple scheduler, CFG 1, 864×480, and 368.746s
|
||||
runtime. **MM-R2V-61** is the quality reference for the 10-second bright
|
||||
park-and-robins prompt. **MM-R2V-62** is the current 10-second speed baseline:
|
||||
SLA attention at 0.85 sparsity / block 32, with acceptable quality and a
|
||||
525.745s runtime. The 0.90 variant was slower in quality terms and is not the
|
||||
baseline.
|
||||
runtime. **MM-R2V-61** is the quality reference for the original 864×480
|
||||
10-second bright park-and-robins prompt. **MM-R2V-68** is now the production
|
||||
baseline at 960×544: SLA 0.85 / block 32, Comfy Kitchen attention, Low-VRAM
|
||||
Attention (4 chunks), and Chunk FeedForward (2 chunks), with 659.169s runtime.
|
||||
|
||||
## Test matrix
|
||||
|
||||
@@ -109,13 +108,13 @@ results and should not be queued automatically with Phase 1.
|
||||
| MM-R2V-59 | J Turbo step comparison | Turbo LoRA only | 12 | res_multistep | beta | 3 | 1.0 | Yes | Yes | No | 551.740 |
|
||||
| MM-R2V-60 | J Turbo step comparison | Turbo LoRA only | 12 | res_multistep | simple | 3 | 1.0 | Yes | Yes | No | 511.753 |
|
||||
| MM-R2V-61 | K duration/prompt | Current Turbo baseline with bright park prompt | 8 | res_multistep | simple | 10 | 1.0 | Yes | Yes | Yes | 790.632 |
|
||||
| MM-R2V-62 | L SLA attention | MM-R2V-61 + H3 SLA Attention, sparsity 0.85, block 32 | 8 | res_multistep | simple | 10 | 1.0 | Yes | Yes | Yes | 525.745 |
|
||||
| MM-R2V-62 | L SLA attention | MM-R2V-61 + H3 SLA Attention, sparsity 0.85, block 32 | 8 | res_multistep | simple | 10 | 1.0 | Yes | Yes | No | 525.745 |
|
||||
| MM-R2V-63 | L SLA attention | MM-R2V-61 + H3 SLA Attention, sparsity 0.90, block 32 | 8 | res_multistep | simple | 10 | 1.0 | Yes | Yes | No | 480.653 |
|
||||
| MM-R2V-64 | M combined attention | SLA 0.85 / block 32 + Sol-Attention | 8 | res_multistep | simple | 10 | 1.0 | Yes | Yes | No | 597.210 |
|
||||
| MM-R2V-65 | M combined attention | SLA 0.85 / block 32 + MiniMax Low-VRAM Attention, 4 head chunks | 8 | res_multistep | simple | 10 | 1.0 | Yes | Yes | No | 552.801 |
|
||||
| MM-R2V-66 | N cache | SLA 0.85 / block 32 + EasyCache defaults (reuse 0.2, 15–95%) | 8 | res_multistep | simple | 10 | 1.0 | Yes | Yes | No | 532.431 |
|
||||
| MM-R2V-67 | O cleanup control | Clean single-reference graph + SLA 0.85 / block 32 | 8 | res_multistep | simple | 10 | 1.0 | Yes | Yes | No | 538.369 |
|
||||
| MM-R2V-68 | P high resolution | 960×544 + SLA 0.85 + Comfy Kitchen backend + Low-VRAM 4 + Chunk FF 2 | 8 | res_multistep | simple | 10 | 1.0 | Queued | — | No | — |
|
||||
| MM-R2V-68 | P high resolution | 960×544 + SLA 0.85 + Comfy Kitchen backend + Low-VRAM 4 + Chunk FF 2 | 8 | res_multistep | simple | 10 | 1.0 | Yes | Yes | Yes | 659.169 |
|
||||
|
||||
## Result requirements
|
||||
|
||||
@@ -149,6 +148,8 @@ MM-R2V-61 was user-reviewed as clean with an acceptable reference match.
|
||||
MM-R2V-62 was judged acceptable but lower quality than MM-R2V-61; its faster
|
||||
runtime makes it the current 10-second speed baseline. MM-R2V-63 was judged
|
||||
acceptable but not as good as MM-R2V-62, so it was not promoted.
|
||||
MM-R2V-68 was user-reviewed as having very good quality and is promoted as
|
||||
the next baseline at 960×544.
|
||||
MM-R2V-64 was user-reviewed as having no visible quality difference from the
|
||||
SLA-only baseline, with the added Sol-Attention cost, so it was not promoted.
|
||||
MM-R2V-65 was user-reviewed as having no clear quality difference from the
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"id":"MM-R2V-68","phase":"P high resolution","status":"success","prompt_id":"110b19dc-4e9a-44d0-88d0-faf811ad0724","resolution":[960,544],"duration_seconds":10,"cfg":1,"steps":8,"sampler":"res_multistep","scheduler":"simple","seed":20260927,"turbo_lora":true,"sla_attention":{"sparsity_ratio":0.85,"block_size":32},"attention_backend":"comfy kitchen attention","low_vram_attention":{"head_chunks":4},"chunk_feedforward":{"chunks":2,"seq_threshold":4096},"runtime_seconds":659.169,"output":{"file":"MM-R2V-68.mp4","sha256":"f8ff5c275472a5e0c0247e673769b5be935a75081d0bebfc27bd1869115a10a4","bytes":1942440},"valid":true,"quality_verdict":"User: quality is really good; promoted as next baseline"
|
||||
}
|
||||
Binary file not shown.
@@ -2,8 +2,8 @@
|
||||
"reference_media": "reference.png (Picture 1)",
|
||||
"prompt": "prompt.txt",
|
||||
"seed": "fixed per comparison batch",
|
||||
"resolution": [864, 480],
|
||||
"duration_seconds": 3,
|
||||
"resolution": [960, 544],
|
||||
"duration_seconds": 10,
|
||||
"cfg": 1,
|
||||
"test_phases": [
|
||||
"A: efficiency nodes and safe combinations",
|
||||
|
||||
Reference in New Issue
Block a user