Sergey

[There are a plenty of configuration files](https://github.com/hukenovs/easyportrait/tree/main/pipelines/local_configs/easyportrait_experiments_v2) for various pre-trained `.pth` (models) provided in the repository which can be used for demo inference. However, there are SINet and ExtremeC3Net `.pth`...

MobileNetV3Large BatchNorm Incompatible With Expected Resource

1

## ❓Question ### Intro Hi! I'm having the following `MobileNetV3Large` model for Semantic Human Segmentation: ```python def create_mobilenet_segmentation_model(input_shape): base_model = tf.keras.applications.MobileNetV3Large(input_shape=input_shape[1:], include_top=False, weights='imagenet') base_model.trainable = True inputs = tf.keras.Input(batch_shape=input_shape) #...

Support gpt-image-1 model for Image Generation

3

Recently, OpenAI has introduced `gpt-image-1` model (https://platform.openai.com/docs/models/gpt-image-1) However, since `gpt-image-1` doesn't obtain `style` field for API request (https://platform.openai.com/docs/api-reference/images/create) it fails with an exception. I also suggest adding missing parameters for...

Support for the OpenAI gpt-image-1 image generation model

2

## Issue Closes #2921 ## Change Added `gpt-image-1` support for OpenAI Image API ## General checklist - [X] There are no breaking changes - [X] I have added unit and/or...