Merge branch 'latest' into dark

Author: Andrei Kochin

.ci/ignore_treon_docker.txt

@@ -26,8 +26,7 @@ notebooks/decidiffusion-image-generation/decidiffusion-image-generation.ipynb
 notebooks/pix2struct-docvqa/pix2struct-docvqa.ipynb
 notebooks/fast-segment-anything/fast-segment-anything.ipynb
 notebooks/latent-consistency-models-image-generation/latent-consistency-models-image-generation.ipynb
-notebooks/latent-consistency-models-image-generation/lcm-lora-controlnet.ipynb
-notebooks/latent-consistency-models-image-generation/latent-consistency-models-optimum-demo.ipynb
+notebooks/lcm-lora-controlnet/lcm-lora-controlnet.ipynb
 notebooks/qrcode-monster/qrcode-monster.ipynb
 notebooks/speculative-sampling/speculative-sampling.ipynb
 notebooks/distil-whisper-asr/distil-whisper-asr.ipynb
@@ -40,6 +39,7 @@ notebooks/stable-diffusion-ip-adapter/stable-diffusion-ip-adapter.ipynb
 notebooks/kosmos2-multimodal-large-language-model/kosmos2-multimodal-large-language-model.ipynb
 notebooks/photo-maker/photo-maker.ipynb
 notebooks/openvoice/openvoice.ipynb
+notebooks/openvoice2-and-melotts/openvoice2-and-melotts.ipynb
 notebooks/surya-line-level-text-detection/surya-line-level-text-detection.ipynb
 notebooks/instant-id/instant-id.ipynb
 notebooks/stable-diffusion-keras-cv/stable-diffusion-keras-cv.ipynb
@@ -87,4 +87,6 @@ notebooks/omniparser/omniparser.ipynb
 notebooks/olmocr-pdf-vlm/olmocr-pdf-vlm.ipynb
 notebooks/minicpm-o-omnimodal-chatbot/minicpm-o-omnimodal-chatbot.ipynb
 notebooks/kokoro/kokoro.ipynb
-notebooks/qwen2.5-omni-chatbot/qwen2.5-omni-chatbot.ipynb
+notebooks/qwen2.5-omni-chatbot/qwen2.5-omni-chatbot.ipynb
+notebooks/intern-video2-classiciation/intern-video2-classification.ipynb
+notebooks/flex.2-image-generation/flex.2-image-generation.ipynb

.ci/skipped_notebooks.yml

@@ -166,13 +166,7 @@
         - macos-13
         - ubuntu-22.04
         - windows-2019
-- notebook: notebooks/latent-consistency-models-image-generation/lcm-lora-controlnet.ipynb
-  skips:
-    - os:
-        - macos-13
-        - ubuntu-22.04
-        - windows-2019
-- notebook: notebooks/latent-consistency-models-image-generation/latent-consistency-models-optimum-demo.ipynb
+- notebook: notebooks/lcm-lora-controlnet/lcm-lora-controlnet.ipynb
   skips:
     - os:
         - macos-13
@@ -536,9 +530,23 @@
         - macos-13
         - ubuntu-22.04
         - windows-2019
-- notebook: "notebooks/deepseek-vl2/deepseek-vl2.ipynb"
+- notebook: notebooks/deepseek-vl2/deepseek-vl2.ipynb
   skips:
     - os:
         - macos-13
         - ubuntu-22.04
-        - windows-2019
+        - windows-2019
+- notebook: notebooks/intern-video2-classiciation/intern-video2-classification.ipynb
+  skips:
+    - os:
+        - macos-13
+        - ubuntu-22.04
+        - windows-2019
+- notebook: notebooks/flex.2-image-generation/flex.2-image-generation.ipynb
+  skips:
+    - python:
+        - "3.9"
+- notebook: notebooks/openvoice2-and-melotts/openvoice2-and-melotts.ipynb
+  skips:
+    - os:
+        - macos-13

.ci/spellcheck/.pyspelling.wordlist.txt

@@ -85,6 +85,7 @@ BLACKBOX
 boolean
 CatVTON
 CentOS
+centric
 CFG
 charlist
 charlists
@@ -405,6 +406,7 @@ intel
 interactable
 InternLM
 internlm
+InternVideo
 Interpolative
 interpretable
 invertible
@@ -548,6 +550,7 @@ md
 MediaPipe
 medprob
 mel
+MeloTTS
 Mels
 MERCHANTABILITY
 MF
@@ -1082,6 +1085,7 @@ vec
 VegaRT
 verovio
 videpth
+ViFM
 VIO
 virtualenv
 VisCPM

.docker/Pipfile.lock

@@ -49,6 +49,7 @@
 - [Text-to-image generation using PhotoMaker and OpenVINO](./photo-maker/photo-maker.ipynb)
 - [Multimodal assistant with Phi-4-multimodal and OpenVINO](./phi-4-multimodal/phi-4-multimodal.ipynb)
 - [Visual-language assistant with Phi3-Vision and OpenVINO](./phi-3-vision/phi-3-vision.ipynb)
+- [Voice tone cloning with OpenVoice2 and MeloTTS for Text-to-Speech by OpenVINO](./openvoice2-and-melotts/openvoice2-and-melotts.ipynb)
 - [Voice tone cloning with OpenVoice and OpenVINO](./openvoice/openvoice.ipynb)
 - [Running OpenCLIP models using OpenVINO™](./open-clip/open-clip.ipynb)
 - [Screen Parsing with OmniParser-v2.0 and OpenVINO](./omniparser/omniparser.ipynb)
@@ -78,7 +79,7 @@
 - [Visual-language assistant with LLaVA Next and OpenVINO](./llava-next-multimodal-chatbot/llava-next-multimodal-chatbot.ipynb)
 - [Visual-language assistant with LLaVA and Optimum Intel OpenVINO integration](./llava-multimodal-chatbot/llava-multimodal-chatbot-optimum.ipynb)
 - [Visual-language assistant with LLaVA and OpenVINO Generative API](./llava-multimodal-chatbot/llava-multimodal-chatbot-genai.ipynb)
-- [Text-to-Image Generation with LCM LoRA and ControlNet Conditioning](./latent-consistency-models-image-generation/lcm-lora-controlnet.ipynb)
+- [Text-to-Image Generation with LCM LoRA and ControlNet Conditioning](./lcm-lora-controlnet/lcm-lora-controlnet.ipynb)
 - [Image generation with Latent Consistency Model and OpenVINO](./latent-consistency-models-image-generation/latent-consistency-models-image-generation.ipynb)
 - [Kosmos-2: Multimodal Large Language Model and OpenVINO](./kosmos2-multimodal-large-language-model/kosmos2-multimodal-large-language-model.ipynb)
 - [Multimodal understanding and generation with Janus-Pro and OpenVINO](./janus-multimodal-generation/janus-multimodal-generation.ipynb)
@@ -147,6 +148,7 @@
 - [Line-level text detection with Surya](./surya-line-level-text-detection/surya-line-level-text-detection.ipynb)
 - [Convert a PyTorch Model to OpenVINO™ IR](./pytorch-to-openvino/pytorch-to-openvino.ipynb)
 - [Convert a PaddlePaddle Model to OpenVINO™ IR](./paddle-to-openvino/paddle-to-openvino-classification.ipynb)
+- [Voice tone cloning with OpenVoice2 and MeloTTS for Text-to-Speech by OpenVINO](./openvoice2-and-melotts/openvoice2-and-melotts.ipynb)
 - [Voice tone cloning with OpenVoice and OpenVINO](./openvoice/openvoice.ipynb)
 - [OpenVINO Tokenizers: Incorporate Text Processing Into OpenVINO Pipelines](./openvino-tokenizers/openvino-tokenizers.ipynb)
 - [Object detection and masking from prompts with GroundedSAM (GroundingDINO + SAM) and OpenVINO](./grounded-segment-anything/grounded-segment-anything.ipynb)
@@ -178,6 +180,7 @@
 - [Person Tracking with OpenVINO™](./person-tracking-webcam/person-tracking.ipynb)
 - [Person Counting System using YOLOV8 and OpenVINO™](./person-counting-webcam/person-counting.ipynb)
 - [PaddleOCR with OpenVINO™](./paddle-ocr-webcam/paddle-ocr-webcam.ipynb)
+- [Voice tone cloning with OpenVoice2 and MeloTTS for Text-to-Speech by OpenVINO](./openvoice2-and-melotts/openvoice2-and-melotts.ipynb)
 - [Voice tone cloning with OpenVoice and OpenVINO](./openvoice/openvoice.ipynb)
 - [Live Object Detection with OpenVINO™](./object-detection-webcam/object-detection.ipynb)
 - [CLIP model with Jina CLIP and OpenVINO](./jina-clip/jina-clip.ipynb)
@@ -250,6 +253,7 @@
 - [Text-to-speech (TTS) with Parler-TTS and OpenVINO](./parler-tts-text-to-speech/parler-tts-text-to-speech.ipynb)
 - [Text-to-Speech synthesis using OuteTTS and OpenVINO](./outetts-text-to-speech/outetts-text-to-speech.ipynb)
 - [Optical Character Recognition (OCR) with OpenVINO™](./optical-character-recognition/optical-character-recognition.ipynb)
+- [Voice tone cloning with OpenVoice2 and MeloTTS for Text-to-Speech by OpenVINO](./openvoice2-and-melotts/openvoice2-and-melotts.ipynb)
 - [Voice tone cloning with OpenVoice and OpenVINO](./openvoice/openvoice.ipynb)
 - [Running OpenCLIP models using OpenVINO™](./open-clip/open-clip.ipynb)
 - [Universal Segmentation with OneFormer and OpenVINO](./oneformer-segmentation/oneformer-segmentation.ipynb)
@@ -284,13 +288,14 @@
 - [Visual-language assistant with LLaVA and Optimum Intel OpenVINO integration](./llava-multimodal-chatbot/llava-multimodal-chatbot-optimum.ipynb)
 - [Visual-language assistant with LLaVA and OpenVINO Generative API](./llava-multimodal-chatbot/llava-multimodal-chatbot-genai.ipynb)
 - [Text-to-Speech synthesis using Llasa and OpenVINO](./llasa-speech-synthesis/llasa-speech-synthesis.ipynb)
-- [Text-to-Image Generation with LCM LoRA and ControlNet Conditioning](./latent-consistency-models-image-generation/lcm-lora-controlnet.ipynb)
+- [Text-to-Image Generation with LCM LoRA and ControlNet Conditioning](./lcm-lora-controlnet/lcm-lora-controlnet.ipynb)
 - [Image generation with Latent Consistency Model and OpenVINO](./latent-consistency-models-image-generation/latent-consistency-models-image-generation.ipynb)
 - [Kosmos-2: Multimodal Large Language Model and OpenVINO](./kosmos2-multimodal-large-language-model/kosmos2-multimodal-large-language-model.ipynb)
 - [Text-to-Speech synthesis using Kokoro and OpenVINO](./kokoro/kokoro.ipynb)
 - [OpenVINO optimizations for Knowledge graphs](./knowledge-graphs-conve/knowledge-graphs-conve.ipynb)
 - [Multimodal understanding and generation with Janus-Pro and OpenVINO](./janus-multimodal-generation/janus-multimodal-generation.ipynb)
 - [Visual-language assistant with InternVL2 and OpenVINO](./internvl2/internvl2.ipynb)
+- [Video Classification with InternVideo2 and OpenVINO](./intern-video2-classiciation/intern-video2-classification.ipynb)
 - [Image Editing with InstructPix2Pix and OpenVINO](./instruct-pix2pix-image-editing/instruct-pix2pix-image-editing.ipynb)
 - [InstantID: Zero-shot Identity-Preserving Generation using OpenVINO](./instant-id/instant-id.ipynb)
 - [Inpainting with OpenVINO GenAI](./inpainting-genai/inpainting-genai.ipynb)
@@ -343,6 +348,7 @@
 - [Quantization Aware Training with NNCF, using PyTorch framework](./pytorch-quantization-aware-training/pytorch-quantization-aware-training.ipynb)
 - [Post-Training Quantization of PyTorch models with NNCF](./pytorch-post-training-quantization-nncf/pytorch-post-training-quantization-nncf.ipynb)
 - [Optimize Preprocessing](./optimize-preprocessing/optimize-preprocessing.ipynb)
+- [Voice tone cloning with OpenVoice2 and MeloTTS for Text-to-Speech by OpenVINO](./openvoice2-and-melotts/openvoice2-and-melotts.ipynb)
 - [Voice tone cloning with OpenVoice and OpenVINO](./openvoice/openvoice.ipynb)
 - [OpenVINO Tokenizers: Incorporate Text Processing Into OpenVINO Pipelines](./openvino-tokenizers/openvino-tokenizers.ipynb)
 - [Quantize NLP models with Post-Training Quantization ​in NNCF](./language-quantize-bert/language-quantize-bert.ipynb)

notebooks/README.md

@@ -0,0 +1,39 @@
+# Image generation with universal control using Flex.2 and OpenVINO
+
+<div class="alert alert-block alert-danger"> <b>Important note:</b> This notebook requires python >= 3.11. Please make sure that your environment fulfill to this requirement before running it </div>
+
+Flex.2 is flexible text-to-image diffusion model based on Flux model architecture with built in support inpainting and universal control - model accepts pose, line, and depth inputs.
+
+<img src="https://github.com/user-attachments/assets/6a9ab66a-387a-4538-8625-2bb3a16072b5" width="1024"> 
+
+More details about model can be found in [model card](https://huggingface.co/ostris/Flex.2-preview).
+
+In this tutorial we consider how to convert and optimize Flex.2 model using OpenVINO.
+
+>**Note**: Some demonstrated models can require at least 32GB RAM for conversion and running.
+
+### Notebook Contents
+
+In this demonstration, you will learn how to perform text-to-image generation using Flex.2 and OpenVINO. 
+
+Example of model work:
+
+![](https://github.com/user-attachments/assets/140685b7-2c5d-4cef-86fb-33df0849ec1a)
+
+The tutorial consists of the following steps:
+
+- Install prerequisites
+- Collect Pytorch model pipeline
+- Convert model to OpenVINO intermediate representation (IR) format 
+- Compress weights using NNCF
+- Prepare OpenVINO Inference pipeline
+- Run Image generation
+- Launch interactive demo
+
+## Installation Instructions
+
+This is a self-contained example that relies solely on its own code.</br>
+We recommend running the notebook in a virtual environment. You only need a Jupyter server to start.
+For further details, please refer to [Installation Guide](../../README.md).
+
+<img referrerpolicy="no-referrer-when-downgrade" src="https://static.scarf.sh/a.png?x-pxid=5b5a4db0-7875-4bfb-bdbd-01698b5b1a77&file=notebooks/flex.2-image-generation/README.md" />