multimodalart's picture
multimodalart HF Staff
Update app.py
2ffa9a9 verified
Raw
History Blame Contribute Delete
17.4 kB
"""MiniMax-H3 Wushu Action LoRA — text-to-video demo for the martial-arts / kung-fu motion LoRA.
This Space is the denoising half of a split MiniMax-H3 deployment:
- The 62 GiB Qwen3-VL text encoder runs in the conditioner Space (`multimodalart/qwen3vl-conditioner`),
called over the gradio API for each request.
- This Space loads the 61.7 GiB transformer + 10.4 GiB VAEs (77.3 GB total) and runs the denoising loop
and the video + audio decode on the GPU.
- The Jojocodex wushu action LoRA (rank 16, `_pruned`) is folded into the transformer weights at startup,
adding human martial-arts motion: punches, kicks, combination forms, staff technique.
- The Comfy-Org MiniMax-H3 Turbo LoRA (4-step) is folded on top, which the LoRA card says is supported
because the `_pruned` file has its `adaln_proj` rows removed.
The LoRA was trained with ai-toolkit on 455 curated wushu clips at 90 frames / 24 fps — so the demo's default
duration is 3.75 s, which is exactly the 90-frame window it saw.
"""
from __future__ import annotations
import math
import os
import tempfile
import time
import traceback
from functools import cache
# Before anything that could initialize CUDA: `import spaces` patches `torch.cuda` so the 72 GiB load can happen
# at startup rather than on GPU time.
import spaces
import gradio as gr
# --- Configuration ---
MODEL_REPO = os.environ.get("H3_MODEL_REPO", "MiniMaxAI/MiniMax-H3")
CONDITIONER_SPACE = os.environ.get("H3_CONDITIONER", "multimodalart/qwen3vl-conditioner")
LORA_REPO = "Jojocodex/minimax-h3-wushu-action-lora"
# `pack` places the transformer at startup, `lazy` moves everything on the first GPU call.
PLACEMENT = os.environ.get("H3_PLACEMENT", "pack").lower()
# cuDNN's fused attention is 10-20% faster than the SDPA default on this pool.
ATTENTION = os.environ.get("H3_ATTENTION", "_native_cudnn").lower()
# The transformer alone is 61.7 GiB, so the 48 GB `large` booking cannot hold it.
GPU_SIZE = os.environ.get("H3_GPU_SIZE", "xlarge")
# --- Canvas definitions (labels are the wire contract with the conditioner) ---
CANVASES = {
# 16:9
"960x544 · 16:9 fast": (544, 960),
"1024x576 · 16:9 fast": (576, 1024),
"1152x640 · 16:9": (640, 1152),
"1280x704 · 16:9": (704, 1280),
"1344x768 · 16:9 full": (768, 1344),
# 9:16
"544x960 · 9:16 fast": (960, 544),
"640x1152 · 9:16": (1152, 640),
"768x1344 · 9:16 full": (1344, 768),
# 1:1
"544x544 · 1:1 fast": (544, 544),
"768x768 · 1:1 full": (768, 768),
# 4:3 / 3:4
"768x576 · 4:3 fast": (576, 768),
"1024x768 · 4:3 full": (768, 1024),
"576x768 · 3:4 fast": (768, 576),
"768x1024 · 3:4 full": (1024, 768),
# 21:9
"1152x512 · 21:9 fast": (512, 1152),
"1536x672 · 21:9 full": (672, 1536),
}
DEFAULT_CANVAS = "960x544 · 16:9 fast"
FPS = 24
FRAMES_PER_CHUNK = 17
LATENTS_PER_CHUNK = 5
MIN_UI_DURATION = 2.0
MAX_UI_DURATION = 14.0
# 3.75 s == 90 frames == 17 * 5 + 5, the clip length the LoRA was trained on.
TRAINED_DURATION = 3.75
DEFAULT_STEPS = 4
DEFAULT_SEED = 42
# The LoRA has no literal trigger token: the card says to activate it with a natural-language *action* description,
# and lists the four technique families it was captioned around. Each cue below is appended to the user's prompt so
# a request lands inside the family the user picked, in the wording the training captions used.
TECHNIQUES: dict[str, str] = {
"Free-form (no cue)": "",
"拳法 · Punches": "fist and punch techniques, fast hand strikes in continuous motion",
"腿法 · Kicks": "kicking techniques, high leg strikes and spinning kicks",
"综合套路 · Combination forms": "a continuous martial arts form, combination techniques flowing one into the next",
"棍法 · Staff": "staff technique, spinning and striking with a long staff",
}
DEFAULT_TECHNIQUE = "Free-form (no cue)"
def snap_frames(seconds: float) -> int:
"""The frame count MiniMax-H3's video VAE can decode: the next `17 * n + 5` at 24 fps."""
frames = max(1, round(float(seconds) * FPS))
while frames % FRAMES_PER_CHUNK != LATENTS_PER_CHUNK:
frames += 1
return frames
def compose_prompt(prompt: str, technique: str = DEFAULT_TECHNIQUE) -> str:
"""The prompt the model is actually conditioned on: the request plus the technique-family cue."""
prompt = (prompt or "").strip()
cue = TECHNIQUES.get(technique or DEFAULT_TECHNIQUE, "")
if not cue:
return prompt
return f"{prompt.rstrip('.,;')}, {cue}"
def lower_duration_floor(seconds: float = MIN_UI_DURATION) -> None:
"""Let the pipeline generate below its 5 s floor — the LoRA's own clips are 3.75 s."""
from diffusers.modular_pipelines.minimax_h3.modular_pipeline import MiniMaxH3ModularPipeline
MiniMaxH3ModularPipeline.min_duration = property(lambda self: float(seconds))
# --- Global state ---
PIPE = None
MANAGER = None
LOAD_ERROR: str | None = None
LOADED_IN: float | None = None
LORA_STATUS: str | None = None
def status() -> str:
if LOAD_ERROR:
return LOAD_ERROR
if PIPE is None:
return f"Loading `{MODEL_REPO}` (transformer + VAEs, 77.3 GB). Watch the Space logs."
return (
f"Ready · transformer + VAEs **bfloat16** · "
f"placement `{PLACEMENT}` · "
f"attention `{ATTENTION}` · "
f"{LORA_STATUS or 'no LoRA'} · "
f"loaded in {LOADED_IN:.0f}s · "
f"conditioner `{CONDITIONER_SPACE}`"
)
def load_models() -> str | None:
"""Load the denoising half at startup."""
global PIPE, MANAGER, LOAD_ERROR, LOADED_IN, LORA_STATUS
if PIPE is not None or LOAD_ERROR is not None:
return LOAD_ERROR
started = time.time()
try:
import torch
from diffusers import ComponentsManager
from h3_split_blocks import MiniMaxH3GeneratorBlocks
lower_duration_floor()
manager = ComponentsManager()
blocks = MiniMaxH3GeneratorBlocks()
print(f"[gen] loading {[c.name for c in blocks.expected_components]} from {MODEL_REPO} ...", flush=True)
pipe = blocks.init_pipeline(MODEL_REPO, components_manager=manager, collection="h3")
pipe.load_components(dtype=torch.bfloat16, trust_remote_code=True)
# Fold the wushu action LoRA (+ the Turbo LoRA) into the bf16 weights.
import h3_lora
LORA_STATUS = h3_lora.apply_lora(pipe.transformer)
if LORA_STATUS:
print(f"[gen] {LORA_STATUS}", flush=True)
pipe.transformer.set_attention_backend(ATTENTION)
if PLACEMENT == "pack":
pipe.transformer.to("cuda")
PIPE = pipe
MANAGER = manager
LOADED_IN = time.time() - started
print(f"[gen] ready in {LOADED_IN:.0f}s", flush=True)
except Exception as error:
traceback.print_exc()
LOAD_ERROR = (
f"**Loading `{MODEL_REPO}` failed** after {time.time() - started:.0f}s: "
f"`{type(error).__name__}: {error}`"
)
return LOAD_ERROR
@cache
def conditioner():
"""The other half, over the gradio API."""
from gradio_client import Client
return Client(CONDITIONER_SPACE)
def encode_remote(prompt, canvas, num_frames):
"""`/encode` on the conditioner Space — text only, this LoRA is text-to-video."""
from safetensors import safe_open
path, plan = conditioner().predict(
prompt=prompt,
image_path=None,
last_image_path=None,
canvas=canvas,
num_frames=num_frames,
rewrite_prompt=False,
api_name="/encode",
)
with safe_open(path, framework="pt") as handle:
return handle.get_tensor("prompt_embeds"), handle.get_tensor("text_token_tags"), handle.metadata(), plan
# --- GPU duration estimation ---
# Fitted on this Space's own ZeroGPU pool (RTX Pro 6000, 4 warm measurements of `_generate` wall time).
# `rows` is the packed latent sequence length, so per-step cost is linear + quadratic (attention) in it:
#
# rows steps measured rows steps measured
# 13770 4 23 s 32560 4 39 s
# 13770 8 33 s 32560 8 73.5 s
#
# -> per-step 2.5 s @ 13770 and 8.6 s @ 32560, which solves to the two coefficients below (+4% headroom).
# The residual fixed cost (audio/video decode, VAE placement) measured 4.5-13 s; 14 s covers it.
_DUR_B = 1.25e-4
_DUR_C = 4.6e-9
_DECODE_FIXED = 14
_PAD = 8
# The very first GPU call of the process also pays VAE placement + cuDNN attention autotune. That one-off is
# both large and very noisy -- the same request that takes 23-27 s warm measured 55 s, 63 s and 78 s cold on
# three different boots -- so it gets a deliberately wide allowance. It is charged once per process, so
# over-booking it costs almost nothing in aggregate while an under-book aborts somebody's first request.
_COLD_START = 70
_WARMED_UP = False
def get_duration(prompt_embeds, text_token_tags, height, width, num_frames, steps, seed, *a, **k):
height, width, num_frames, steps = int(height), int(width), int(num_frames), int(steps)
latent_frames = (num_frames - LATENTS_PER_CHUNK) // FRAMES_PER_CHUNK * LATENTS_PER_CHUNK + 2
rows = latent_frames * (height // 32) * (width // 32)
denoise = steps * (_DUR_B * rows + _DUR_C * rows**2)
seconds = denoise + _DECODE_FIXED + _PAD
if not _WARMED_UP:
seconds += _COLD_START
return int(math.ceil(seconds))
@spaces.GPU(duration=get_duration, size=GPU_SIZE)
def _generate(prompt_embeds, text_token_tags, height, width, num_frames, steps, seed):
"""The only thing on GPU time: the packed-sequence denoise loop and the two decoders."""
import torch
if PLACEMENT == "lazy":
PIPE.to("cuda")
elif PLACEMENT == "pack":
PIPE.vae.to("cuda")
PIPE.audio_vae.to("cuda")
state = PIPE(
prompt_embeds=prompt_embeds.to("cuda"),
text_token_tags=text_token_tags,
image=None,
last_image=None,
height=int(height),
width=int(width),
num_frames=int(num_frames),
num_inference_steps=int(steps),
generator=torch.Generator("cpu").manual_seed(int(seed)),
)
return state.get("videos")[0], state.get("audio")[0].cpu(), state.get("sampling_rate")
def generate(
prompt,
technique=DEFAULT_TECHNIQUE,
canvas=DEFAULT_CANVAS,
duration=TRAINED_DURATION,
steps=DEFAULT_STEPS,
seed=DEFAULT_SEED,
progress=gr.Progress(track_tqdm=True),
):
"""Generate a martial-arts action clip with the MiniMax-H3 wushu action LoRA.
Parameters:
prompt: What the fighter does, e.g. "a kung fu practitioner executing a spinning kick"
technique: Technique family cue appended to the prompt (punches / kicks / forms / staff)
canvas: Output resolution and aspect ratio
duration: Clip length in seconds, snapped to the 17n+5 frames the video VAE decodes
steps: Denoising steps (4 with the Turbo LoRA folded in)
seed: Random seed for reproducibility
"""
if LOAD_ERROR:
raise gr.Error(LOAD_ERROR)
if PIPE is None:
raise gr.Error("The denoiser is still loading. Please wait a moment and try again.")
if not prompt or not prompt.strip():
raise gr.Error("Please describe the martial-arts action you want, e.g. 'a fighter throws a spinning kick'.")
from diffusers.utils import encode_video
full_prompt = compose_prompt(prompt, technique)
num_frames = snap_frames(duration)
progress(0.0, desc=f"Conditioning on {CONDITIONER_SPACE} ...")
conditioned = time.time()
prompt_embeds, text_token_tags, metadata, plan = encode_remote(full_prompt, canvas, num_frames)
condition_seconds = time.time() - conditioned
height, width, num_frames = (int(metadata[key]) for key in ("height", "width", "num_frames"))
progress(0.1, desc=f"Denoising {int(steps)} steps at {width}x{height}, {num_frames} frames ...")
started = time.time()
frames, audio, sampling_rate = _generate(
prompt_embeds, text_token_tags, height, width, num_frames, steps, seed
)
generate_seconds = time.time() - started
# Placement and kernel autotune are paid once; later requests book the (much smaller) warm estimate.
global _WARMED_UP
_WARMED_UP = True
directory = os.path.join(tempfile.gettempdir(), "h3-outputs")
os.makedirs(directory, exist_ok=True)
path = os.path.join(directory, f"h3-wushu-{int(time.time() * 1000)}.mp4")
encode_video(frames, fps=FPS, output_path=path, audio=audio, audio_sample_rate=sampling_rate)
report = (
f"**Prompt sent to the model:** {full_prompt}\n\n"
f"`{width}x{height}`, {num_frames} frames ({num_frames / FPS:.2f} s), {int(steps)} steps · "
f"seed {int(seed)} · conditioner {condition_seconds:.0f}s ({plan['num_text_tokens']} tokens) · "
f"denoise + decode {generate_seconds:.0f}s ({generate_seconds / max(int(steps), 1):.1f} s/step)"
)
print(f"[gen] {report}", flush=True)
return path, report
# --- Load models at startup ---
load_models()
INTRO = """# 武打动作 · MiniMax-H3 Wushu Action LoRA
<div>
<a href="https://huggingface.co/Jojocodex/minimax-h3-wushu-action-lora" target="_blank" rel="noopener"><strong>[ LoRA ]</strong></a> &nbsp;
<a href="https://huggingface.co/MiniMaxAI/MiniMax-H3" target="_blank" rel="noopener"><strong>[ base model ]</strong></a> &nbsp;
<a href="https://huggingface.co/Comfy-Org/MiniMax-H3" target="_blank" rel="noopener"><strong>[ ComfyUI weights ]</strong></a>
</div>
Generate short **martial-arts / kung-fu action** clips — punches, kicks, forms, staff work — with
[MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3) and the
[Wushu Action LoRA](https://huggingface.co/Jojocodex/minimax-h3-wushu-action-lora), trained on 455 curated wushu
clips at 90 frames / 24 fps. The video comes back with H3's native synchronized soundtrack.
The LoRA has **no trigger token** — it activates on the action description itself. Describe the strike, then pick a
technique family to steer it toward the wording its captions used. Generation takes roughly a minute.
"""
CSS = """
.main.fillable {max-width: 1250px !important}
.dark .gradio-container { color: var(--body-text-color); }
"""
with gr.Blocks(title="MiniMax-H3 Wushu Action LoRA") as demo:
gr.Markdown(INTRO)
with gr.Row(equal_height=True):
with gr.Column():
prompt = gr.Textbox(
label="Action",
lines=3,
placeholder="e.g. 'a kung fu practitioner executing a spinning kick on a temple courtyard'",
value="a martial artist performing punches and kicks in fast combat",
)
technique = gr.Radio(
label="Technique family",
info="Appended to the prompt in the wording the LoRA's captions used.",
choices=list(TECHNIQUES),
value=DEFAULT_TECHNIQUE,
)
run = gr.Button("Generate", variant="primary", size="lg")
with gr.Accordion("Advanced options", open=False):
canvas = gr.Dropdown(label="Canvas", choices=list(CANVASES), value=DEFAULT_CANVAS)
duration = gr.Slider(
label="Duration (s)",
info="Snapped up to the next 17n+5 frames. The LoRA was trained at 90 frames (3.75 s).",
minimum=MIN_UI_DURATION,
maximum=MAX_UI_DURATION,
step=0.25,
value=TRAINED_DURATION,
)
steps = gr.Slider(
label="Steps",
info="4 is enough with the Turbo LoRA folded in — more steps mostly just cost GPU time.",
minimum=4,
maximum=12,
step=5,
value=DEFAULT_STEPS,
)
seed = gr.Number(label="Seed", value=DEFAULT_SEED, precision=0)
with gr.Column():
video = gr.Video(label="Video + soundtrack", autoplay=True)
report = gr.Markdown()
gr.Examples(
examples=[
["a martial artist performing punches and kicks in fast combat", "Free-form (no cue)"],
["a kung fu practitioner executing a spinning kick", "腿法 · Kicks"],
["two fighters exchanging strikes in an intense fight", "Free-form (no cue)"],
["a martial artist performing a powerful roundhouse kick, with explosive force", "腿法 · Kicks"],
["a practitioner demonstrating a fast flurry of punches in continuous motion", "拳法 · Punches"],
["a fighter executing a spinning staff technique", "棍法 · Staff"],
["a wushu athlete running through a form in a courtyard at dawn", "综合套路 · Combination forms"],
],
inputs=[prompt, technique],
outputs=[video, report],
fn=generate,
cache_examples=True,
cache_mode="lazy",
)
inputs = [prompt, technique, canvas, duration, steps, seed]
run.click(generate, inputs, [video, report], api_name="generate")
prompt.submit(generate, inputs, [video, report], api_name=False)
if __name__ == "__main__":
demo.launch(show_error=True, theme=gr.themes.Citrus(), css=CSS, max_threads=1000)