97ac841518
- Extract model loading from generate()/edit() into VnAssetsSession class - Session eagerly loads SDXL + Qwen Image Edit at construction (28s, once) - Both models held in GPU memory across calls; generate()/edit() reuse them - generate.py and edit.py become thin wrappers (backwards compatible CLI) - Context manager (with VnAssetsSession(...) as vna:) for library use - Metadata backwards-compatible: all fields preserved including lora_load_s - load_time_s now reflects total session construction, amortized across calls - Add performance stats for edit path (Qwen Image Edit + Lightning LoRA) - Benchmark matmul fallback (86.8s) vs flash attention (53.3s, 1.63x speedup) - Session vs cold start comparison: 2 ops save one 28s load, 5 edits save 112s - Flash attention via TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 documented
32 lines
832 B
Python
32 lines
832 B
Python
"""Qwen Image Edit — image-to-image editing (standalone entry point).
|
|
|
|
For multi-call reuse, use VnAssetsSession directly.
|
|
"""
|
|
from .session import VnAssetsSession
|
|
|
|
|
|
def edit(
|
|
model_path: str,
|
|
input_path: str,
|
|
prompt: str,
|
|
steps: int = 20,
|
|
cfg: float = 4.0,
|
|
seed: int | None = None,
|
|
output_path: str = "output.png",
|
|
lora_path: str | None = None,
|
|
) -> None:
|
|
"""One-shot image edit. Loads model, runs inference, unloads.
|
|
|
|
For multiple edits, create a VnAssetsSession to keep the model
|
|
loaded between calls.
|
|
"""
|
|
with VnAssetsSession(edit_model=model_path, edit_lora=lora_path) as vna:
|
|
vna.edit(
|
|
input_path=input_path,
|
|
prompt=prompt,
|
|
steps=steps,
|
|
cfg=cfg,
|
|
seed=seed,
|
|
output_path=output_path,
|
|
)
|