#!/bin/bash
# Start ImageEditServer with forged SVDQuant NVFP4 r32 Qwen-Image-2.1 model
# Runs 100% resident in VRAM on GPU 0 with Heretic text encoder by default
# Default: 25 steps, guidance-scale 1.0, port 4500, Text Encoder: Qwen21_Text_Encoder_Heretic

PORT=${1:-4500}
MODEL_DIR="/home/olegk/Nikola/models/Qwen/Qwen-Image-2.1"
OPTIMIZED_MODEL="/home/olegk/Nikola/models/nunchaku-qwen-image-2.1/best_quality_fp4.safetensors"
TEXT_ENCODER=${2:-"/home/olegk/Nikola/models/Qwen21_Text_Encoder_Heretic"}

echo "=========================================================="
echo "Starting ImageEditServer (Qwen-Image-2.1 SVDQuant NVFP4 - Resident VRAM)"
echo "Port: $PORT"
echo "Model: $MODEL_DIR"
echo "Optimized Model: $OPTIMIZED_MODEL"
echo "Text Encoder: $TEXT_ENCODER"
echo "Steps: 25 | Guidance Scale: 1.0 | Resident Mode: True"
echo "=========================================================="

export CUDA_VISIBLE_DEVICES="0"
export PYTORCH_CUDA_ALLOC_CONF="expandable_segments:True"
export PYTHONPATH="/home/olegk/Nikola/packages/nunchaku:/home/olegk/Nikola/packages/deepcompressor:/home/olegk/Nikola:$PYTHONPATH"

cd /auto/home/amano/olegk/Nikola/src/imagegen

EXTRA_ARGS=""
if [ -n "$TEXT_ENCODER" ] && [ "$TEXT_ENCODER" != "none" ]; then
    EXTRA_ARGS="--text-encoder $TEXT_ENCODER"
fi

exec /home/olegk/Nikola/.venv/bin/python ImageEditServer.py \
    --host 0.0.0.0 \
    --port "$PORT" \
    --model "$MODEL_DIR" \
    --optimized-model "$OPTIMIZED_MODEL" \
    --backend qwen21-nvfp4 \
    --steps 25 \
    --guidance-scale 1.0 \
    $EXTRA_ARGS