Text-To-Video¶

#!/bin/bash
# HunyuanVideo-1.5 text-to-video curl example using the async video job API.

set -euo pipefail

BASE_URL="${BASE_URL:-http://localhost:8098}"
OUTPUT_PATH="${OUTPUT_PATH:-hunyuan_video_15_t2v.mp4}"
POLL_INTERVAL="${POLL_INTERVAL:-2}"

create_response=$(
  curl -sS -X POST "${BASE_URL}/v1/videos" \
    -H "Accept: application/json" \
    -F "prompt=A little girl wearing a straw hat runs through a summer meadow full of wildflowers. A wide shot is used, with the camera panning right to follow her." \
    -F "size=832x480" \
    -F "num_frames=33" \
    -F "fps=24" \
    -F "num_inference_steps=30" \
    -F "guidance_scale=6.0" \
    -F "flow_shift=5.0" \
    -F "seed=42"
)

video_id="$(echo "${create_response}" | jq -r '.id')"
if [ -z "${video_id}" ] || [ "${video_id}" = "null" ]; then
  echo "Failed to create video job:"
  echo "${create_response}" | jq .
  exit 1
fi

echo "Created video job ${video_id}"
echo "${create_response}" | jq .

while true; do
  status_response="$(curl -sS "${BASE_URL}/v1/videos/${video_id}")"
  status="$(echo "${status_response}" | jq -r '.status')"

  case "${status}" in
    queued|in_progress)
      echo "Video job ${video_id} status: ${status}"
      sleep "${POLL_INTERVAL}"
      ;;
    completed)
      echo "${status_response}" | jq .
      break
      ;;
    failed)
      echo "Video generation failed:"
      echo "${status_response}" | jq .
      exit 1
      ;;
    *)
      echo "Unexpected status response:"
      echo "${status_response}" | jq .
      exit 1
      ;;
  esac
done

curl -sS -L "${BASE_URL}/v1/videos/${video_id}/content" -o "${OUTPUT_PATH}"
echo "Saved video to ${OUTPUT_PATH}"

#!/bin/bash
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
#
# LTX-2 text-to-video curl example using the async video job API.
# Start the server first: bash run_server_ltx2.sh best-combo

set -euo pipefail

BASE_URL="${BASE_URL:-http://localhost:8098}"
OUTPUT_PATH="${OUTPUT_PATH:-ltx2_output.mp4}"
POLL_INTERVAL="${POLL_INTERVAL:-2}"

PROMPT="${PROMPT:-A serene lakeside sunrise with mist over the water.}"

create_response=$(
  curl -sS -X POST "${BASE_URL}/v1/videos" \
    -H "Accept: application/json" \
    -F "prompt=${PROMPT}" \
    -F "width=768" \
    -F "height=480" \
    -F "num_frames=41" \
    -F "fps=24" \
    -F "num_inference_steps=20" \
    -F "guidance_scale=3.0" \
    -F "seed=42"
)

video_id="$(echo "${create_response}" | jq -r '.id')"
if [ -z "${video_id}" ] || [ "${video_id}" = "null" ]; then
  echo "Failed to create video job:"
  echo "${create_response}" | jq .
  exit 1
fi

echo "Created video job ${video_id}"
echo "${create_response}" | jq .

while true; do
  status_response="$(curl -sS "${BASE_URL}/v1/videos/${video_id}")"
  status="$(echo "${status_response}" | jq -r '.status')"

  case "${status}" in
    queued|in_progress)
      echo "Video job ${video_id} status: ${status}"
      sleep "${POLL_INTERVAL}"
      ;;
    completed)
      echo "${status_response}" | jq .
      break
      ;;
    failed)
      echo "Video generation failed:"
      echo "${status_response}" | jq .
      exit 1
      ;;
    *)
      echo "Unexpected status response:"
      echo "${status_response}" | jq .
      exit 1
      ;;
  esac
done

curl -sS -L "${BASE_URL}/v1/videos/${video_id}/content" -o "${OUTPUT_PATH}"
echo "Saved video to ${OUTPUT_PATH}"

#!/bin/bash
# Wan2.2 text-to-video curl example using the async video job API.

set -euo pipefail

BASE_URL="${BASE_URL:-http://localhost:8098}"
OUTPUT_PATH="${OUTPUT_PATH:-wan22_output.mp4}"
POLL_INTERVAL="${POLL_INTERVAL:-2}"

create_response=$(
  curl -sS -X POST "${BASE_URL}/v1/videos" \
    -H "Accept: application/json" \
    -F "prompt=Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage." \
    -F "seconds=2" \
    -F "size=832x480" \
    -F "negative_prompt=色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走" \
    -F "fps=16" \
    -F "num_inference_steps=40" \
    -F "guidance_scale=4.0" \
    -F "guidance_scale_2=4.0" \
    -F "boundary_ratio=0.875" \
    -F "flow_shift=5.0" \
    -F "seed=42"
)

video_id="$(echo "${create_response}" | jq -r '.id')"
if [ -z "${video_id}" ] || [ "${video_id}" = "null" ]; then
  echo "Failed to create video job:"
  echo "${create_response}" | jq .
  exit 1
fi

echo "Created video job ${video_id}"
echo "${create_response}" | jq .

while true; do
  status_response="$(curl -sS "${BASE_URL}/v1/videos/${video_id}")"
  status="$(echo "${status_response}" | jq -r '.status')"

  case "${status}" in
    queued|in_progress)
      echo "Video job ${video_id} status: ${status}"
      sleep "${POLL_INTERVAL}"
      ;;
    completed)
      echo "${status_response}" | jq .
      break
      ;;
    failed)
      echo "Video generation failed:"
      echo "${status_response}" | jq .
      exit 1
      ;;
    *)
      echo "Unexpected status response:"
      echo "${status_response}" | jq .
      exit 1
      ;;
  esac
done

curl -sS -L "${BASE_URL}/v1/videos/${video_id}/content" -o "${OUTPUT_PATH}"
echo "Saved video to ${OUTPUT_PATH}"

#!/bin/bash
# Wan2.2 online serving startup script

MODEL="${MODEL:-Wan-AI/Wan2.2-T2V-A14B-Diffusers}"
PORT="${PORT:-8098}"
BOUNDARY_RATIO="${BOUNDARY_RATIO:-0.875}"
FLOW_SHIFT="${FLOW_SHIFT:-5.0}"
CACHE_BACKEND="${CACHE_BACKEND:-none}"
ENABLE_CACHE_DIT_SUMMARY="${ENABLE_CACHE_DIT_SUMMARY:-0}"

echo "Starting Wan2.2 server..."
echo "Model: $MODEL"
echo "Port: $PORT"
echo "Boundary ratio: $BOUNDARY_RATIO"
echo "Flow shift: $FLOW_SHIFT"
echo "Cache backend: $CACHE_BACKEND"
if [ "$ENABLE_CACHE_DIT_SUMMARY" != "0" ]; then
    echo "Cache-DiT summary: enabled"
fi

CACHE_BACKEND_FLAG=""
if [ "$CACHE_BACKEND" != "none" ]; then
    CACHE_BACKEND_FLAG="--cache-backend $CACHE_BACKEND"
fi

vllm serve "$MODEL" --omni \
    --port "$PORT" \
    --boundary-ratio "$BOUNDARY_RATIO" \
    --flow-shift "$FLOW_SHIFT" \
    $CACHE_BACKEND_FLAG \
    $(if [ "$ENABLE_CACHE_DIT_SUMMARY" != "0" ]; then echo "--enable-cache-dit-summary"; fi)

#!/bin/bash
# HunyuanVideo-1.5 text-to-video online serving startup script
#
# 480p: ~35 GB VRAM (BF16), fits 1x A100 80GB
# 720p: needs FP8 + VAE tiling, ~35 GB VRAM

MODEL="${MODEL:-hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v}"
PORT="${PORT:-8098}"
FLOW_SHIFT="${FLOW_SHIFT:-5.0}"
QUANTIZATION="${QUANTIZATION:-}"
CACHE_BACKEND="${CACHE_BACKEND:-none}"

echo "Starting HunyuanVideo-1.5 T2V server..."
echo "Model: $MODEL"
echo "Port: $PORT"
echo "Flow shift: $FLOW_SHIFT"
echo "Quantization: ${QUANTIZATION:-none}"
echo "Cache backend: $CACHE_BACKEND"

EXTRA_FLAGS=""
if [ -n "$QUANTIZATION" ]; then
    EXTRA_FLAGS="$EXTRA_FLAGS --quantization $QUANTIZATION"
fi
if [ "$CACHE_BACKEND" != "none" ]; then
    EXTRA_FLAGS="$EXTRA_FLAGS --cache-backend $CACHE_BACKEND"
fi

vllm serve "$MODEL" --omni \
    --port "$PORT" \
    --flow-shift "$FLOW_SHIFT" \
    $EXTRA_FLAGS

#!/bin/bash
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
#
# LTX-2 online serving startup script with optimization presets.
#
# Usage:
#   bash run_server_ltx2.sh                  # baseline (1 GPU, eager)
#   bash run_server_ltx2.sh ulysses4         # 4-GPU Ulysses SP
#   bash run_server_ltx2.sh cache-dit        # 1 GPU + Cache-DiT
#   bash run_server_ltx2.sh best-combo       # 4-GPU Ulysses SP + Cache-DiT
#
# Online serving benchmarks on H800 (480×768, 41 frames, 20 steps):
#   baseline    : 10.3s inference (1.00×)
#   compile     : ~10.3s warm     (~1.00×) first request +6s warmup
#   ulysses4    : ~10.3s          (~1.00×) no gain at 41 frames
#   cache-dit   :  7.4s avg       (~1.4×)  lossy, variable per request
#   best-combo  :  4.7s avg       (~2.2×)  4-GPU ulysses + cache-dit

set -euo pipefail

MODEL="${MODEL:-Lightricks/LTX-2}"
PORT="${PORT:-8098}"
FLOW_SHIFT="${FLOW_SHIFT:-1.0}"
BOUNDARY_RATIO="${BOUNDARY_RATIO:-1.0}"

PRESET="${1:-baseline}"

EXTRA_ARGS=()
case "$PRESET" in
    baseline)
        echo "=== LTX-2 Preset: baseline (1 GPU, enforce-eager) ==="
        EXTRA_ARGS+=(--enforce-eager)
        ;;
    ulysses2)
        echo "=== LTX-2 Preset: 2-GPU Ulysses SP (lossless) ==="
        EXTRA_ARGS+=(--enforce-eager --usp 2)
        ;;
    ulysses4)
        echo "=== LTX-2 Preset: 4-GPU Ulysses SP (lossless) ==="
        EXTRA_ARGS+=(--enforce-eager --usp 4)
        ;;
    cache-dit)
        echo "=== LTX-2 Preset: Cache-DiT (1 GPU, lossy) ==="
        EXTRA_ARGS+=(--enforce-eager --cache-backend cache_dit)
        ;;
    best-combo)
        echo "=== LTX-2 Preset: 4-GPU Ulysses SP + Cache-DiT (best combo) ==="
        EXTRA_ARGS+=(--enforce-eager --usp 4 --cache-backend cache_dit)
        ;;
    compile)
        echo "=== LTX-2 Preset: torch.compile (1 GPU, lossless) ==="
        # torch.compile is the default (no --enforce-eager)
        ;;
    *)
        echo "Usage: $0 {baseline|ulysses2|ulysses4|cache-dit|best-combo|compile}"
        echo ""
        echo "Presets:"
        echo "  baseline    - 1 GPU, eager execution (reference)"
        echo "  ulysses2    - 2-GPU Ulysses SP (lossless)"
        echo "  ulysses4    - 4-GPU Ulysses SP (lossless)"
        echo "  cache-dit   - 1 GPU + Cache-DiT (lossy, ~1.4× speedup)"
        echo "  best-combo  - 4-GPU Ulysses SP + Cache-DiT (~2.2× speedup)"
        echo "  compile     - 1 GPU + torch.compile (slower first request)"
        echo ""
        echo "Environment variables:"
        echo "  MODEL           - Model path (default: Lightricks/LTX-2)"
        echo "  PORT            - Server port (default: 8098)"
        echo "  FLOW_SHIFT      - Scheduler flow shift (default: 1.0)"
        echo "  BOUNDARY_RATIO  - Boundary ratio (default: 1.0)"
        exit 1
        ;;
esac

echo "Model: $MODEL"
echo "Port: $PORT"
echo "Flow shift: $FLOW_SHIFT"
echo "Boundary ratio: $BOUNDARY_RATIO"

vllm serve "$MODEL" --omni \
    --port "$PORT" \
    --flow-shift "$FLOW_SHIFT" \
    --boundary-ratio "$BOUNDARY_RATIO" \
    "${EXTRA_ARGS[@]}"