[BugFIX] enable Hunyuan image3 with stage selection among text_to_image/image_to_text (#1826)

Signed-off-by: Chendi Xue <chendi.xue@intel.com>

examples/offline_inference/hunyuan_image3/image_to_text.py

@@ -60,10 +60,13 @@ def main(args: argparse.Namespace) -> None:
     omni = Omni(
         model=args.model,
         enable_diffusion_pipeline_profiler=args.enable_diffusion_pipeline_profiler,
+        mode="image-to-text",
     )
 
+    prompt = "<|startoftext|>You are an assistant that understands images and outputs text.<img>" + args.prompt
+
     prompt_dict = {
-        "prompt": args.prompt,
+        "prompt": prompt,
         "modalities": ["text"],
     }
 

examples/offline_inference/text_to_image/text_to_image.py

@@ -317,6 +317,7 @@ def main():
         "parallel_config": parallel_config,
         "enforce_eager": args.enforce_eager,
         "enable_cpu_offload": args.enable_cpu_offload,
+        "mode": "text-to-image",
         "enable_diffusion_pipeline_profiler": args.enable_diffusion_pipeline_profiler,
         **lora_args,
         **quant_kwargs,