Add sparse latent upscale MiniMax test workflow
This commit is contained in:
@@ -6,6 +6,7 @@ MiniMax baseline is a validated 10-second, 960×544 workflow; the earlier
|
||||
3-second/480p efficiency tests remain recorded as historical comparisons.
|
||||
|
||||
- [`minimax/`](minimax/) — MiniMax H3 R2V base and efficiency matrix
|
||||
- [`minimax/sparse-latent-upscale/`](minimax/sparse-latent-upscale/) — supplied Fast H3 sparse-attention and tiled latent-upscale study
|
||||
|
||||
Current baseline: MiniMax MM-R2V-68, Turbo LoRA, SLA 0.85, Comfy Kitchen
|
||||
attention, Low-VRAM Attention, and Chunk FeedForward at 8 steps, Res
|
||||
|
||||
Reference in New Issue
Block a user