Collect SLA 0.90 R2V result
This commit is contained in:
@@ -34,8 +34,11 @@ 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 accepted 10-second baseline with the brighter
|
||||
park-and-robins prompt, using the same settings and 790.632s runtime.
|
||||
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.
|
||||
|
||||
## Test matrix
|
||||
|
||||
@@ -106,8 +109,8 @@ 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 | 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 | Queued | — | No | — |
|
||||
| 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-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 |
|
||||
|
||||
## Result requirements
|
||||
|
||||
@@ -137,8 +140,10 @@ present in the live API graph. They must not be substituted with the plain
|
||||
Turbo/base graph. MM-R2V-51 through MM-R2V-58 completed with the validated
|
||||
Turbo graph. User review promoted MM-R2V-58 for its environment quality and
|
||||
lower runtime; MM-R2V-59/60 did not justify the additional 12-step runtime.
|
||||
MM-R2V-61 was user-reviewed as clean with an acceptable reference match and
|
||||
is the accepted 10-second baseline.
|
||||
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.
|
||||
|
||||
## Execution order
|
||||
|
||||
|
||||
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"id":"MM-R2V-63","phase":"L SLA attention","status":"success","prompt_id":"ab164797-993c-4bf8-abd0-b39a29120871","resolution":[864,480],"duration_seconds":10,"cfg":1,"steps":8,"sampler":"res_multistep","scheduler":"simple","seed":20260927,"turbo_lora":true,"sla_attention":{"sparsity_ratio":0.9,"block_size":32},"runtime_seconds":480.653,"output":{"file":"MM-R2V-63.mp4","sha256":"7e760657ac3b9946406dd5c83541b00d659edbcda0dd18a497e512ba5718af09","bytes":1929717},"valid":true,"quality_verdict":"User: quality acceptable but lower than MM-R2V-62; do not promote"
|
||||
}
|
||||
Binary file not shown.
Reference in New Issue
Block a user