Add genai to sdxl-turbo

[aleksandr-mokrov]

CVS-161647

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

eaidova commented on 2025-02-06T04:28:59Z
----------------------------------------------------------------

Line #29.        optimum_cli(sdxl_model_id, model_dir, additional_args={"weight-format": "fp16", "task": "stable-diffusion-xl"})

task is not obligated and if you specify it, it is better to use more generic name text-to-image

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

eaidova commented on 2025-02-06T04:29:00Z
----------------------------------------------------------------

Line #11.        optimum_cli(sdxl_model_id, model_dir_int8, additional_args={"weight-format": "fp16", "task": "stable-diffusion-xl"})

not sure that you need convert model twice, when you can just copy content.

I think we can move this utility to notebook_utils.py and reuse it for such cases

openvino_notebooks/notebooks/nano-llava-multimodal-chatbot/ov_nano_llava_helper.py

Line 15 in 15a8276

def copy_model_files(src_dir, dst_dir, ignore_llm=True, ignore_vision_encoder=True):