VideoRebirthAI/hyperflow-h3-flash

HyperFlow H3 Flash (14B)

By downloading or using these weights, you accept the MiniMax H3 Community License Agreement. The Agreement restricts territory (not licensed in the EU, UK, South Korea, or the US without prior authorization from MiniMax) and includes an Acceptable Use Policy. See License. This repository is not an official MiniMax product.

HyperFlow H3 Flash is Video Rebirth's compressed, few-step version of MiniMax-H3. It generates video and synchronized stereo audio together.

Showcase: See HyperFlow H3 Flash generated video and audio examples.

• Output: a 5.2 to 15 s video at 24 fps (1344×768 by default) with a 32 kHz stereo soundtrack.
• Sampling: 4, 6, or 8 steps without classifier-free guidance (CFG). The default is 6 steps.
• Speed (5.2 s clip, 6 steps): 8.7 s on 4× B200, 36 s on 1× H200, and 92 s on an RTX 5090.
• Real time on 4× Blackwell GPUs: NVIDIA SOL-H3 runs HyperFlow H3 Flash in real time on 4× B-series GPUs. SOL-H3 is our inference-acceleration partner and supports this model from day 0.
• Model size: 13.7B (fl2va) or 13.9B (ref2va) parameters, less than half of the ~31B MiniMax-H3 transformer.
• Minimum footprint: Q4_K_M is 9.1 GB (Q8_0 is 14.9 GB). It runs on 24 GB and 32 GB GPUs in PCs with 16 GB of system RAM. 16 GB GPUs are not measured yet.

Code, setup guides, and ComfyUI workflows are in Video-Rebirth/hyperflow-h3-flash. For the 8-step LoRA on the full-size MiniMax-H3 transformer, see VideoRebirthAI/hyperflow (GitHub).

Supported Tasks

Task	Input	Hub partition	ComfyUI template	GGUF support	Python INT8 support
t2va	Text prompt	fl2va_*	hyperflow_t2v	Yes	Yes
fl2va	Prompt + first keyframe, or first and last keyframes	fl2va_*	hyperflow_i2v, hyperflow_flf2v	Yes	Yes
ref2va	Prompt + up to 12 references	ref2va_*	hyperflow_ref2v	Images only	Images, videos, and audio

---

Choose a Weight Format

Decision rule: Use GGUF on any PC with 64 GB of system RAM or less. Use INT8 convrot on data-center GPUs, or on 24 GB+ RTX GPUs with at least 69 GiB of system RAM.

Feature	GGUF	INT8 convrot
Hub folders	fl2va_gguf/, ref2va_gguf/	fl2va_int8_convrot/, ref2va_int8_convrot/
Precision & size	Q3_K_M to Q8_0 (7.2–15.2 GB)	W8A8 INT8 + low-rank (~16 GB)
Runtime	ComfyUI, Unsloth Studio, stable-diffusion.cpp	hyperflow-h3-flash CLI and diffusers
Target GPU	Consumer GPUs; measured on 24 GB and 32 GB RTX GPUs (16 GB GPUs not measured yet)	H100 / H200 / B200 / B300 (1–8 GPUs), or 24 GB+ RTX GPUs
System RAM	16 GB+	~16 GiB without offload; ≥ 69 GiB (fp8 text encoder) or ≥ 91 GiB (bf16) with offload
ref2va inputs	Images	Images, videos, and audio

---

Repository Layout and Companion Files

fl2va_int8_convrot/    config.json, diffusion_pytorch_model-0000{1..3}-of-00003.safetensors (+ index), model code
ref2va_int8_convrot/   config.json, diffusion_pytorch_model-0000{1..4}-of-00004.safetensors (+ index), model code
fl2va_gguf/            minimax_h3_fl2va_hyperflow_flash_14b-<QUANT>.gguf (6 quant levels)
ref2va_gguf/           minimax_h3_ref2va_hyperflow_flash_14b-<QUANT>.gguf (6 quant levels)

This repository stores only the compressed transformers (transformer for fl2va, transformer_ref for ref2va). Each runtime loads the shared text encoder, video VAE, audio VAE, tokenizer, and processor from their upstream repositories:

Runtime	Companion text encoder and VAEs
hyperflow-h3-flash (Python)	Downloads automatically from MiniMaxAI/MiniMax-H3, or from Qwen/Qwen3-VL-32B-Instruct-FP8 with --text-encoder-precision fp8. Never downloads the 62 GB base transformer.
ComfyUI & stable-diffusion.cpp	Comfy-Org/MiniMax-H3: text_encoders/qwen3vl_32b_minimax_h3_*.safetensors (nvfp4_awq 15.7 GB, int8_convrot 27.1 GB, or bf16 51.5 GB), vae/minimax_h3_video_vae_fp16.safetensors, vae/minimax_h3_audio_vae_fp32.safetensors
Unsloth Studio	Downloads automatically from unsloth/MiniMax-H3-GGUF

---

GGUF (ComfyUI, Unsloth Studio, stable-diffusion.cpp)

Quant	fl2va_gguf/	ref2va_gguf/	Recipe	When to use
Q4_K_M	9.1 GB	9.2 GB	Q4_K (lifted layers Q6_K)	Recommended default for 24 GB GPUs
Q8_0	14.9 GB	15.2 GB	Q8_0	Closest to full precision when VRAM and RAM fit
Q6_K	11.6 GB	11.8 GB	Q6_K	High quality, smaller than Q8_0
Q5_K_M	10.3 GB	10.5 GB	Q5_K (lifted layers Q6_K)	Balanced intermediate quant
Q4_K_S	8.0 GB	8.1 GB	Q4_K	Compact 4-bit quant
Q3_K_M	7.2 GB	7.4 GB	Q3_K (lifted layers Q5_K)	Smallest footprint

Full setup instructions are in integrations/README.md. Summary:

• ComfyUI:
  1. Clone ComfyUI-GGUF and ComfyUI-HyperFlow-Flash into ComfyUI/custom_nodes/.
  2. Put the .gguf file in models/diffusion_models/ and download the 15.7 GB qwen3vl_32b_minimax_h3_nvfp4_awq text encoder.
  3. On 16 GB or 32 GB RAM PCs, start ComfyUI with python main.py --fast-disk.
  4. Open Workflow > Browse Templates > ComfyUI-HyperFlow-Flash and select hyperflow_t2v, hyperflow_i2v, hyperflow_flf2v, or hyperflow_ref2v.
• Unsloth Studio: Point SD_CLI_PATH at the patched sd-cli binary (export SD_CLI_PATH=/path/to/stable-diffusion.cpp/build/bin/sd-cli), run unsloth studio, and load VideoRebirthAI/hyperflow-h3-flash (fl2va_gguf/ or ref2va_gguf/). Studio downloads the companion files and runs the 6-step schedule at CFG = 1.
• stable-diffusion.cpp: Apply integrations/stable-diffusion.cpp/hyperflow-two-time.patch to upstream commit 3be2378, build, and run:

  sd-cli -M vid_gen \
    --diffusion-model minimax_h3_fl2va_hyperflow_flash_14b-Q4_K_M.gguf \
    --llm qwen3vl_32b_minimax_h3_bf16.safetensors \
    --vae minimax_h3_video_vae_fp16.safetensors \
    --audio-vae minimax_h3_audio_vae_fp32.safetensors \
    --sampling-method euler --cfg-scale 1.0 --steps 6 \
    -W 1344 -H 768 --video-frames 124 --fps 24 -s 42 \
    -p "A chef slides a steaming bowl of ramen across a wooden counter; rain taps on the window." \
    -o output.webm
  

  Add -i first.png (and --end-img last.png) for keyframes. Use minimax_h3_ref2va_... with --ref-image a.png --ref-image b.png for reference images. Add --offload-to-cpu on smaller GPUs.

---

INT8 convrot (hyperflow-h3-flash & diffusers)

Install

pip install git+https://github.com/Video-Rebirth/hyperflow-h3-flash
pip install "hyperflow-h3-flash[hopper] @ git+https://github.com/Video-Rebirth/hyperflow-h3-flash"  # H100 / H200: FlashAttention-3
pip install "hyperflow-h3-flash[fp8] @ git+https://github.com/Video-Rebirth/hyperflow-h3-flash"     # --text-encoder-precision fp8

• Requirements: Python 3.10+, PyTorch 2.6+ with CUDA and Triton (pip install triton-windows on native Windows), an Ampere or newer NVIDIA GPU, and diffusers >= 0.40. Multi-GPU (--gpus > 1) requires Linux or WSL2.
• First run: Downloads 90 GB (68 GB with --text-encoder-precision fp8), covering the text encoder, VAEs, and the 16 GB INT8 transformer for the selected task. Triton INT8 kernels compile on first use (~1 min).

Command Line

# Text to video + audio (t2va)
hyperflow-h3-flash --prompt "A chef slides a steaming bowl of ramen across a wooden counter; rain taps on the window." \
    --output ramen.mp4

# First keyframe, or first + last keyframe (fl2va)
hyperflow-h3-flash --prompt "..." --image first.png --last-image last.png --output clip.mp4

# Reference images, videos, and audio clips in prompt order (ref2va)
hyperflow-h3-flash --prompt "<Picture 1> walks through the scene of <Picture 2> ..." \
    --reference person.png --reference scene.png --output clip.mp4

# 15 s clip across 4 GPUs; or fp8 text encoder to save ~22 GiB system RAM when offloading
hyperflow-h3-flash --prompt "..." --num-frames 360 --gpus 4
hyperflow-h3-flash --prompt "..." --steps 4 --text-encoder-precision fp8

Option	Values (default)	Description
--steps	4, 6 (6), 8	4 for speed, 6 balanced, 8 for quality
--num-frames	124–362 (124)	5.2 to 15 s at 24 fps; rounds up to 17n + 5
--gpus	1, 2, 4, 7, 8, auto	Context and VAE tile parallelism under torchrun
--offload	auto (auto), none, model, stream	none needs ≥ 90 GiB VRAM; model/stream need ≥ 91 GiB RAM (bf16) or ≥ 69 GiB (fp8)
--text-encoder-precision	bf16 (bf16), fp8	fp8 saves ~22 GiB system RAM when offloading (requires [fp8])
--attention	auto (auto), sdpa, fa3	Uses FlashAttention-3 (fa3) on Hopper when kernels is installed
--block-chunk	0 (0), 16384, ...	Slice token-wise block ops (--block-chunk 16384 fits 15 s mixed ref2va on 24 GB GPUs)

Python API (load_pipeline)

import torch
from diffusers.utils.export_utils import encode_video
from hyperflow_h3_flash import load_pipeline

pipe = load_pipeline("t2va")  # "fl2va": pass image=... (and last_image=...); "ref2va": pass references=[...]
out = pipe(
    prompt="A chef slides a steaming bowl of ramen across a wooden counter; rain taps on the window.",
    num_frames=124,
    num_inference_steps=6,  # 4, 6, or 8
    generator=torch.Generator().manual_seed(0),
    output=["videos", "audio", "sampling_rate"],
)
encode_video(
    out["videos"][0],
    fps=24,
    output_path="ramen.mp4",
    audio=out["audio"][0],
    audio_sample_rate=out["sampling_rate"],
)

Standalone Transformer (AutoModel)

Each INT8 folder ships hyperflow_h3_flash_transformer.py and hyperflow_h3_flash_int8.py. AutoModel loads the transformer without installing hyperflow-h3-flash:

import torch
from diffusers import AutoModel

model = AutoModel.from_pretrained(
    "VideoRebirthAI/hyperflow-h3-flash",
    subfolder="fl2va_int8_convrot",  # or "ref2va_int8_convrot"
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
)
model.pad_lowrank_ranks()  # pad low-rank dimensions to multiples of 64 for aligned GEMMs
model.to("cuda")

# Optional on Hopper GPUs (requires `pip install kernels`):
model.set_attention_backend("_flash_3_hub")

Note: The transformer requires endpoint_timestep on every forward pass for two-time (t, r) conditioning. Use load_pipeline or hyperflow_h3_flash.flash_blocks to run the full sampling loop.

---

Benchmarks and Memory

All benchmarks measure end-to-end generation (text encoding, 6-step transformer, and video and audio VAE decode) at 1344×768 and 6 steps. Clip lengths: 5.2 s = 124 frames; 15 s = 362 frames.

1. Consumer RTX GPUs (5.2 s / 15 s total time)

GPU	GGUF Q4_K_M (ComfyUI) ≥ 64 GB RAM	GGUF --fast-disk 32 GB PC	GGUF --fast-disk 16 GB PC	INT8 (hyperflow-h3-flash)¹ --offload stream
RTX 5090 (32 GB)	99 s / 575 s	118 s / 618 s	130 s / 615 s	92 s / 551 s
RTX 4090 (24 GB)	157 s / 830 s	151 s / 815 s	153 s / 812 s	130 s / 750 s
RTX 3090 (24 GB)	315 s / 1835 s	318 s / 1869 s	325 s / 1866 s	266 s / 1684 s
Peak VRAM (5.2 s / 15 s)	5090: 28 / 27 GiB; 24 GB: 23 / 22 GiB	same as ≥ 64 GB	same as ≥ 64 GB	12.0–12.5 / 21.8–22.4 GiB

• GGUF columns: Use the 15.7 GB nvfp4_awq text encoder. --fast-disk streams unresident weights from the OS file page cache instead of pinned RAM, keeping anonymous RSS at ~8–16 GiB.
• ¹ INT8 column: Requires ≥ 91 GiB system RAM with the bf16 text encoder, or ~69 GiB with --text-encoder-precision fp8.

Reference to video (ref2va) on one RTX GPU (5.2 s / 15 s total time):

GPU	INT8, 2 images	INT8, mixed²	GGUF match, 2 images	GGUF max, 2 images
RTX 5090 (32 GB)	266 s / 914 s	503 s / 1318 s	135 s / 660 s	295 s / 995 s³
RTX 4090 (24 GB)	319 s / 1167 s	630 s / 1702 s⁴	194 s / 885 s	398 s / 1275 s³
RTX 3090 (24 GB)	726 s / 2763 s	1441 s / 4033 s⁴	401 s / 2059 s	885 s / 2995 s³

• ² Mixed: One reference image, one 5.2 s reference video with soundtrack, and one audio clip. ³ Start ComfyUI with --disable-cuda-malloc for max at 15 s. ⁴ Pass --block-chunk 16384 on 24 GB GPUs for 15 s mixed ref2va. On 32 GB / 16 GB PCs with --fast-disk, 2-image ref2v (match) runs in 139 s / 663 s and 157 s / 684 s on RTX 5090, 180 s / 866 s and 178 s / 876 s on RTX 4090, and 385 s / 2010 s and 384 s / 2025 s on RTX 3090.

2. Data-Center GPUs (hyperflow-h3-flash INT8)

GPUs	--offload	5.2 s (124 frames)	15 s (362 frames)	Peak VRAM / GPU (5.2 s / 15 s)	System RAM / GPU
1× H200 (141 GB)	none	36 s	229 s	80 / 91 GiB	16 GiB
2× H200 (141 GB)	none	24 s	119 s	— / 71 GiB	16 GiB
4× H200 (141 GB)	none	12.6 s	66 s	47 / 59 GiB	16 GiB
4× B200	none	8.7 s	—	46 GiB	16 GiB

The table measures the hyperflow-h3-flash package. For real time on 4× B-series GPUs, use NVIDIA SOL-H3.

---

Step Schedules and Prompting

Step Grids

Both partitions and both weight formats share three unshifted sigma grids (video_shift = 12, audio_shift = 3):

Steps	Mode	Raw sigmas
4	Speed	1, 0.681872, 0.205019, 0.036496, 0
6	Balanced (default)	1, 0.825217, 0.471725, 0.147401, 0.049626, 0.015517, 0
8	Quality	1, 0.931506, 0.839236, 0.703462, 0.5, 0.296538, 0.160764, 0.068494, 0

Prompts

• Describe the subject, action, setting, camera movement, and sound in one prompt. Do not use a negative prompt (CFG = 1.0).
• For ref2va, name inputs in prompt order as <Picture i>, <Video i>, and <Audio i>. Limits: 9 images, 3 videos, 3 audio clips, and 12 references total. Audio references require at least one image or video reference. GGUF runtimes accept image references only; video and audio references require the Python package.

---

How It Works

1. Structural pruning and low-rank factorization: fl2va drops 3 of 50 blocks (6, 21, 22) and factors 102 linear layers (13.7B parameters). ref2va drops 1 of 50 blocks (9) and factors 114 linear layers (13.9B parameters).
2. Rotated W8A8 INT8 (convrot): 180 linear layers are quantized to W8A8 INT8 behind a block-diagonal Hadamard rotation. Kernels dispatch to fused Triton (sm_80–sm_90, sm_120), cuBLASLt INT8 (sm_100), or BF16 tensor cores (sm_103 B300).
3. Two-time (t, r) conditioning: Every token receives the current noise level t and the step endpoint r. This enables 4-to-8-step sampling without CFG.

---

Acknowledgements

Thanks to the MiniMax team for releasing MiniMax-H3, to Unsloth for the MiniMax-H3 GGUF layout and naming convention, to WAS/Minimax-h3_Singularity_v2_pruned for pioneering rotated INT8 on MiniMax-H3, and to stable-diffusion.cpp, ComfyUI, and ComfyUI-GGUF.

Intended Use and Limitations

• HyperFlow H3 Flash provides fast, reduced-memory joint video and stereo audio generation across data-center and consumer GPUs (4–8 steps, 7.2–16 GB transformer weights).
• Prompt adherence, supported languages, biases, and failure modes follow the MiniMax-H3 base model.
• Every use of these weights is bound by the license terms below, including territorial restrictions and the Acceptable Use Policy.

License

The transformer weights in this repository (both INT8 convrot and GGUF) are a Model Derivative of MiniMax-H3 and are distributed under the MiniMax H3 Community License Agreement with no additional terms. By downloading or using them, you accept that Agreement:

• Territory: Licensed worldwide excluding the European Union, the United Kingdom, the Republic of Korea, and the United States of America. Individuals and organizations in those jurisdictions must obtain MiniMax's prior authorization before downloading (application form; License Q&A).
• Redistribution: Include a copy of the Agreement and the NOTICE file, clearly mark modified files, and do not impose additional or different terms (Section III).
• AI-Generated Content Disclosure: Publicly distributed content generated with these weights must be clearly disclosed as AI-generated (Acceptable Use Policy, item 12).
• Commercial Use: Products or services exceeding $20 million USD in annual revenue require prior written authorization from MiniMax (api@minimax.io). Products and services built with the weights must prominently display "MiniMax H3" on their user interface (Section IV.2).
• Hosted Services & Use Restrictions: Hosted services must implement the safeguards in Section V.5 and bind end users to Section V and the Acceptable Use Policy (Exhibit A). Outputs may not be used to train or improve other AI models.
• Upstream Text: LICENSE reproduces the August 2, 2026 Agreement text; the version in the upstream repository governs.

See NOTICE for the architectural and numerical modifications from MiniMax-H3. The inference code on GitHub is licensed separately under Apache-2.0 (ComfyUI custom node under GPL-3.0; stable-diffusion.cpp patch under MIT).

HyperFlow H3 Flash is developed by Video Rebirth and is not an official MiniMax product. Powered by MiniMax H3.