HyperFlow H3 Flash INT8 (convrot) β€” FL2VA Γ— REF2VA aligned hybrid b25-49

A community hybrid of the two HyperFlow H3 Flash INT8 convrot transformers from BennyDaBall/HyperFlow-H3-Flash-INT8-ComfyUI: the FL2VA file is the base, and source blocks 25–49 take on the REF2VA model's AdaLN modulation.

Unlike a plain tensor swap, the replaced adaln_proj weights are re-fitted to the FL2VA time embedder, so the blocks reproduce what REF2VA's modulation actually does (see Why aligned below). A plain swap of the same tensors breaks first/last-frame adherence; this file does not.

Unofficial. Not made, reviewed or endorsed by MiniMax, Video Rebirth, Comfy Org or BennyDaBall.

File

File Size sha256
minimax_h3_hyperflow_flash_hybrid_aligned_fl2va_ref2va_b25-49_int8_convrot.safetensors 15.9 GB e15967787d8836f53fae931a82ae93bbb8973b15bba74a512f0ba0443b50a6b0

Same format as the FL2VA source: ComfyUI MiniMax-H3 layout, INT8 convrot, 47 blocks, loads in the HyperFlow INT8 Loader and the official HyperFlow Loader. Header keeps the FL2VA hyperflow / hyperflow_int8 entries and adds hyperflow_hybrid describing the merge.

What changed

FL2VA HyperFlow Flash INT8 convrot           (base: every INT8 code, row scale, low-rank pair,
        |                                     embedder, gate and sigma tensor is byte-identical)
        +-- source blocks 25-49: adaln_proj.linear.weight / .bias  <- REF2VA modulation, re-fitted (BF16)
        +-- final_layer.adaln_proj                                 <- FL2VA (unchanged)
  • 50 BF16 tensors rewritten (25 blocks Γ— weight + bias). Nothing was dequantized or requantized.
  • The two source files are pruned differently (FL2VA drops source blocks 6, 21, 22 β†’ 47 blocks; REF2VA drops 9 β†’ 49 blocks), so blocks are matched by their original source block index from each file's hyperflow_int8.layout: source block b is blocks.{b-3} in FL2VA and blocks.{b-1} in REF2VA.

Why aligned

Each block's adaln_proj reads silu(t_emb), and t_emb comes from the model's own time_embedder (blended with the HyperFlow endpoint embedder, gate 0.25). FL2VA and REF2VA were distilled separately and their time embeddings differ a lot (50–140 % relative difference over the 6-step schedule), while the modulation each model actually produces differs by only 2–5 %. Measured at the six HyperFlow (t, r) pairs:

per block, relative L2 of the modulation blocks 25–49
FL2VA vs REF2VA (each with its own embedder) 1.6–4.1 %
plain swap (REF2VA weights fed FL2VA's embedding) vs REF2VA 8.6–13 %
aligned (this file) vs REF2VA 0.17 %

The fit: for every replaced block, find Wβ€², bβ€² with Wβ€² Β· silu(emb_FL2VA(t, r)) + bβ€² β‰ˆ W_REF2VA Β· silu(emb_REF2VA(t, r)) + b_REF2VA by least squares over a dense (t, r) grid plus the 6-step pairs (weighted). Both sides are linear in the augmented weights, so this is one shared 17Γ—17 map applied to each block.

Test renders

RTX 5060 Ti 16 GB, ComfyUI 0.31.0, 1344Γ—768, 124 frames, 6 steps, euler, CFG 1, seed 42, patcher: legacy.

first/last frame comparison

First + last frame to video, frames 0 / 60 / 123. Top: FL2VA. Middle: this file. Bottom: plain swap of the same tensors (not published): it ignores the keyframes and re-renders the scene.

aligned, dense vs sparse attention

This file. Rows 1–2: flf2v dense / Sol sparse attention. Rows 3–4: t2v dense / Sol. Row 5: ref2v with the plain swap. Row 6: ref2v with this file + Sol.

this file, 16 GB card total sampling s/step peak VRAM
t2v, dense attention 395 s 330 s 51.8 15.4 GB
flf2v, dense attention 584 s 486 s 65.2 15.8 GB
t2v, Sol sparse attention 301 s 237 s 22.8 14.1 GB
flf2v, Sol sparse attention 284 s 205 s 30.6 15.7 GB
ref2v, Sol sparse attention 262 s 190 s 26.4 15.7 GB

On a 16 GB card about 9.5 GB of the weights stay in system RAM (64 GB here) and stream in each step. Loading the file from a 7200 rpm HDD adds about 80–90 s to the first run.

Use in ComfyUI

Exactly like the FL2VA file of the source repo: put the file in ComfyUI/models/diffusion_models/, install ComfyUI-HyperFlow-Flash and comfyui_hyperflow_int8_nodes, and use the source repo's fl2va workflows (t2v, i2v, flf2v) with this file selected in the loader. It also ran the reference-to-video workflow in our tests. Text encoder and VAEs: Comfy-Org/MiniMax-H3. Recommended: HyperFlow Sigmas 6 steps, euler, CFG 1, patcher: legacy.

Tips from testing on an RTX 50 card with a cu128 PyTorch:

  • Start ComfyUI with --enable-triton-backend. Without CUDA 13 PyTorch, comfy_kitchen's CUDA backend is off and INT8 convrot falls back to the slow eager path (~300 s/step here instead of ~52).
  • Sparse attention (about 2.3Γ— faster per step here): the MiniMax-H3 Sol-Attn nodes from ComfyUI-sol-attn (MiniMaxH3MemoryEfficientSolAttentionPatch tau 1.3, MiniMaxH3FusedModulation, MiniMaxH3ChunkFeedForward 2) work with HyperFlow models, but the pack checks for the exact class name MiniMaxH3Model and leaves HyperFlow's subclass unpatched ("expected a MiniMax H3 model"). Changing those checks to also accept subclasses is enough. Sparse attention is an approximation; t2v compositions can differ from dense runs.

License and notices

These files are a Model Derivative of MiniMax-H3, modified from HyperFlow H3 Flash, distributed under the MiniMax H3 Community License Agreement with no additional or different terms; LICENSE and NOTICE ship with them as required, and the modification is recorded in NOTICE and in the file's metadata. The Agreement's territory, commercial-use, use-restriction and AI-generated-content disclosure terms apply β€” read it before downloading. Example images in examples/ are frames of AI-generated video.

Not an official MiniMax product. Powered by MiniMax H3.

Credits: MiniMax (MiniMax H3), Video Rebirth (HyperFlow H3 Flash), BennyDaBall (INT8 convrot solve and ComfyUI conversion), Comfy Org (INT8 convrot kernels), NVIDIA (Sol-Attn).

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for hoidhxd/HyperFlow-H3-Flash-INT8-ComfyUI-Hybrid