Some updates to Text 2 image pipeline

[ilya-lavrenov]

TODO:

• Python API and sample
• Update doc strings
• Update main README.md (PR Readme draft #930)
• Add sample with custom device mapping
• Experiment with reshape + compile as part of Ctor
• Add LoRA (PR LoRA in Text2ImagePipeline #911)
• Use std::optional for prompt2, prompt3 and maybe negative prompts as well
• Update https://github.com/openvinotoolkit/openvino.genai/blob/master/src/docs/SUPPORTED_MODELS.md with text 2 image generation models