|
| 1 | +# Copyright (c) 2026, NVIDIA CORPORATION. All rights reserved. |
| 2 | +# |
| 3 | +# Licensed under the Apache License, Version 2.0 (the "License"); |
| 4 | +# you may not use this file except in compliance with the License. |
| 5 | +# You may obtain a copy of the License at |
| 6 | +# |
| 7 | +# http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | +# |
| 9 | +# Unless required by applicable law or agreed to in writing, software |
| 10 | +# distributed under the License is distributed on an "AS IS" BASIS, |
| 11 | +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| 12 | +# See the License for the specific language governing permissions and |
| 13 | +# limitations under the License. |
| 14 | + |
| 15 | +set -euo pipefail |
| 16 | + |
| 17 | +# Environment variables expected from CI template: |
| 18 | +# CONFIG_PATH, TEST_LEVEL, NPROC_PER_NODE, TEST_NODE_COUNT, |
| 19 | +# MASTER_ADDR, MASTER_PORT, SLURM_JOB_ID, PIPELINE_DIR, TEST_NAME |
| 20 | + |
| 21 | +DATA_DIR="$PIPELINE_DIR/$TEST_NAME/data" |
| 22 | +CKPT_DIR="$PIPELINE_DIR/$TEST_NAME/checkpoint" |
| 23 | +INFER_DIR="$PIPELINE_DIR/$TEST_NAME/inference_output" |
| 24 | + |
| 25 | +cd /opt/Automodel |
| 26 | + |
| 27 | +# ============================================ |
| 28 | +# Derive model-specific settings from config |
| 29 | +# ============================================ |
| 30 | +RECIPE_NAME=$(basename "$CONFIG_PATH" .yaml) |
| 31 | +case "$RECIPE_NAME" in |
| 32 | + wan2_1_t2v_flow*) |
| 33 | + MEDIA_TYPE="video" |
| 34 | + PROCESSOR="wan" |
| 35 | + GENERATE_CONFIG="examples/diffusion/generate/configs/generate_wan.yaml" |
| 36 | + MODEL_NAME="Wan-AI/Wan2.1-T2V-1.3B-Diffusers" |
| 37 | + INFER_NUM_FRAMES=9 |
| 38 | + PREPROCESS_EXTRA_ARGS="" |
| 39 | + ;; |
| 40 | + hunyuan_t2v_flow*) |
| 41 | + MEDIA_TYPE="video" |
| 42 | + PROCESSOR="hunyuan" |
| 43 | + GENERATE_CONFIG="examples/diffusion/generate/configs/generate_hunyuan.yaml" |
| 44 | + MODEL_NAME="hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v" |
| 45 | + INFER_NUM_FRAMES=5 |
| 46 | + PREPROCESS_EXTRA_ARGS="--target_frames 13" |
| 47 | + ;; |
| 48 | + flux_t2i_flow*) |
| 49 | + MEDIA_TYPE="image" |
| 50 | + PROCESSOR="flux" |
| 51 | + GENERATE_CONFIG="examples/diffusion/generate/configs/generate_flux.yaml" |
| 52 | + MODEL_NAME="black-forest-labs/FLUX.1-dev" |
| 53 | + PREPROCESS_EXTRA_ARGS="" |
| 54 | + ;; |
| 55 | + qwen_image_t2i_flow*) |
| 56 | + MEDIA_TYPE="image" |
| 57 | + PROCESSOR="qwen_image" |
| 58 | + GENERATE_CONFIG="examples/diffusion/generate/configs/generate_qwen_image.yaml" |
| 59 | + MODEL_NAME="Qwen/Qwen-Image" |
| 60 | + PREPROCESS_EXTRA_ARGS="" |
| 61 | + ;; |
| 62 | + *) |
| 63 | + echo "ERROR: Unknown recipe '$RECIPE_NAME'. Add a case to diffusion_finetune_launcher.sh." |
| 64 | + exit 1 |
| 65 | + ;; |
| 66 | +esac |
| 67 | +echo "[config] Recipe=$RECIPE_NAME MediaType=$MEDIA_TYPE Processor=$PROCESSOR Model=$MODEL_NAME" |
| 68 | + |
| 69 | +# ============================================ |
| 70 | +# Stage 1: Download dataset |
| 71 | +# ============================================ |
| 72 | +echo "============================================" |
| 73 | +echo "[data] Downloading dataset..." |
| 74 | +echo "============================================" |
| 75 | +if [ "$MEDIA_TYPE" = "image" ]; then |
| 76 | + uv run --extra diffusion python -c " |
| 77 | +from datasets import load_dataset |
| 78 | +from pathlib import Path |
| 79 | +import json |
| 80 | +
|
| 81 | +ds = load_dataset('diffusers/tuxemon', split='train') |
| 82 | +out_dir = Path('$DATA_DIR/raw') |
| 83 | +out_dir.mkdir(parents=True, exist_ok=True) |
| 84 | +
|
| 85 | +jsonl_entries = [] |
| 86 | +for i, row in enumerate(ds): |
| 87 | + fname = f'tuxemon_sample_{i:04d}.png' |
| 88 | + row['image'].save(out_dir / fname) |
| 89 | + jsonl_entries.append({'file_name': fname, 'internvl': row['gpt4_turbo_caption']}) |
| 90 | +
|
| 91 | +jsonl_path = out_dir / 'tuxemon_internvl.json' |
| 92 | +with open(jsonl_path, 'w') as jf: |
| 93 | + for entry in jsonl_entries: |
| 94 | + jf.write(json.dumps(entry) + '\n') |
| 95 | +
|
| 96 | +print(f'Extracted {len(ds)} images to {out_dir}') |
| 97 | +" |
| 98 | +else |
| 99 | + uv run --extra diffusion python -c " |
| 100 | +from huggingface_hub import snapshot_download |
| 101 | +snapshot_download('modal-labs/dissolve', repo_type='dataset', local_dir='$DATA_DIR/raw') |
| 102 | +print('Dataset downloaded successfully') |
| 103 | +" |
| 104 | +fi |
| 105 | + |
| 106 | +# ============================================ |
| 107 | +# Stage 2: Preprocess to latents |
| 108 | +# ============================================ |
| 109 | +echo "============================================" |
| 110 | +echo "[preprocess] Converting ${MEDIA_TYPE}s to latents..." |
| 111 | +echo "============================================" |
| 112 | +if [ "$MEDIA_TYPE" = "image" ]; then |
| 113 | + uv run --extra diffusion python -m tools.diffusion.preprocessing_multiprocess image \ |
| 114 | + --image_dir "$DATA_DIR/raw" \ |
| 115 | + --output_dir "$DATA_DIR/cache" \ |
| 116 | + --processor "$PROCESSOR" \ |
| 117 | + $PREPROCESS_EXTRA_ARGS |
| 118 | +else |
| 119 | + uv run --extra diffusion python -m tools.diffusion.preprocessing_multiprocess video \ |
| 120 | + --video_dir "$DATA_DIR/raw" \ |
| 121 | + --output_dir "$DATA_DIR/cache" \ |
| 122 | + --processor "$PROCESSOR" \ |
| 123 | + --resolution_preset 512p \ |
| 124 | + --caption_format sidecar \ |
| 125 | + $PREPROCESS_EXTRA_ARGS |
| 126 | +fi |
| 127 | + |
| 128 | +# ============================================ |
| 129 | +# Stage 3: Finetune |
| 130 | +# ============================================ |
| 131 | +echo "============================================" |
| 132 | +echo "[finetune] Running finetuning..." |
| 133 | +echo "============================================" |
| 134 | +CONFIG="--config /opt/Automodel/${CONFIG_PATH} \ |
| 135 | + --data.dataloader.cache_dir $DATA_DIR/cache \ |
| 136 | + --checkpoint.checkpoint_dir $CKPT_DIR \ |
| 137 | + --step_scheduler.max_steps ${MAX_STEPS:-100} \ |
| 138 | + --step_scheduler.ckpt_every_steps 100 \ |
| 139 | + --step_scheduler.save_checkpoint_every_epoch false \ |
| 140 | + --fsdp.dp_size ${NPROC_PER_NODE} \ |
| 141 | + --wandb.mode disabled" |
| 142 | + |
| 143 | +CMD="uv run --extra diffusion torchrun --nproc-per-node=${NPROC_PER_NODE} \ |
| 144 | + --nnodes=${TEST_NODE_COUNT} \ |
| 145 | + --rdzv_backend=c10d \ |
| 146 | + --rdzv_endpoint=${MASTER_ADDR}:${MASTER_PORT} \ |
| 147 | + --rdzv_id=${SLURM_JOB_ID}" |
| 148 | + |
| 149 | +eval $CMD examples/diffusion/finetune/finetune.py $CONFIG |
| 150 | + |
| 151 | +# ============================================ |
| 152 | +# Stage 4: Inference smoke test |
| 153 | +# ============================================ |
| 154 | +echo "============================================" |
| 155 | +echo "[inference] Running inference smoke test..." |
| 156 | +echo "============================================" |
| 157 | +CKPT_STEP_DIR=$(ls -d $CKPT_DIR/epoch_*_step_* | sort -t_ -k4 -n | tail -1) |
| 158 | + |
| 159 | +if [ "$MEDIA_TYPE" = "image" ]; then |
| 160 | + uv run --extra diffusion python examples/diffusion/generate/generate.py \ |
| 161 | + --config "$GENERATE_CONFIG" \ |
| 162 | + --model.pretrained_model_name_or_path "$MODEL_NAME" \ |
| 163 | + --model.checkpoint "$CKPT_STEP_DIR" \ |
| 164 | + --inference.num_inference_steps 5 \ |
| 165 | + --output.output_dir "$INFER_DIR" \ |
| 166 | + --vae.enable_slicing true \ |
| 167 | + --vae.enable_tiling true |
| 168 | + |
| 169 | + if ls $INFER_DIR/sample_*.png 1>/dev/null 2>&1; then |
| 170 | + echo "[inference] SUCCESS: Output image(s) generated" |
| 171 | + else |
| 172 | + echo "[inference] FAILURE: No output images found" |
| 173 | + exit 1 |
| 174 | + fi |
| 175 | +else |
| 176 | + uv run --extra diffusion python examples/diffusion/generate/generate.py \ |
| 177 | + --config "$GENERATE_CONFIG" \ |
| 178 | + --model.pretrained_model_name_or_path "$MODEL_NAME" \ |
| 179 | + --model.checkpoint "$CKPT_STEP_DIR" \ |
| 180 | + --inference.num_inference_steps 5 \ |
| 181 | + --inference.pipeline_kwargs.num_frames "$INFER_NUM_FRAMES" \ |
| 182 | + --output.output_dir "$INFER_DIR" \ |
| 183 | + --vae.enable_slicing true \ |
| 184 | + --vae.enable_tiling true |
| 185 | + |
| 186 | + if ls $INFER_DIR/sample_*.mp4 1>/dev/null 2>&1; then |
| 187 | + echo "[inference] SUCCESS: Output video(s) generated" |
| 188 | + else |
| 189 | + echo "[inference] FAILURE: No output videos found" |
| 190 | + exit 1 |
| 191 | + fi |
| 192 | +fi |
0 commit comments