diff --git a/optimized/R2V/minimax/README.md b/optimized/R2V/minimax/README.md index 64d643a..ec431a8 100644 --- a/optimized/R2V/minimax/README.md +++ b/optimized/R2V/minimax/README.md @@ -120,7 +120,7 @@ their row explicitly overrides resolution or duration. | 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 | Yes | Yes | Yes | 659.169 | -| MM-R2V-69 | Q H3 LongVideos | Two fixed 10-second shots: robins, then squirrel joins; full baseline attention/memory chain | 8 | res_multistep | simple | 20 | 1.0 | Queued | — | No | — | +| MM-R2V-69 | Q H3 LongVideos | Two fixed 10-second shots: robins, then squirrel joins; full baseline attention/memory chain | 8 | res_multistep | simple | 20 | 1.0 | Yes | Blocked | No | — | ## Result requirements @@ -166,6 +166,13 @@ MM-R2V-67 was user-reviewed as quality-consistent with the previous SLA baseline, confirming that removing the duplicate reference and unused nodes did not change the result quality. +MM-R2V-69 is blocked by the live server's missing H3-compatible text encoder. +The available `qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors` emits 5120 +features, while H3 LongVideos requires the 2560-feature +`qwen3vl_32b_h3_ultra_uncensored_heretic_int8_convrot.safetensors` referenced +by the imported workflow. Do not substitute another encoder; install or +restore the H3-compatible model before rerunning. + ## Execution order 1. Use MM-R2V-68 as the current 960×544/10-second baseline. diff --git a/optimized/R2V/minimax/h3-longvideos.md b/optimized/R2V/minimax/h3-longvideos.md index 1a6cc23..58c93d8 100644 --- a/optimized/R2V/minimax/h3-longvideos.md +++ b/optimized/R2V/minimax/h3-longvideos.md @@ -31,6 +31,11 @@ paragraph-driven shot plan; it does not load or encode a previous video. - `reference.png` — fixed character reference - `prompt.txt` — shared reference-to-video prompt source +The live server must also provide the H3-compatible 2560-feature text encoder +`qwen3vl_32b_h3_ultra_uncensored_heretic_int8_convrot.safetensors`. The +currently listed 5120-feature `qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors` +is not compatible with `H3LongVideos`. + ## Why this candidate The installed `H3LongVideos` node supports paragraph-driven shot chaining,