Update readme

[SamitHuang]

What does this PR do?

Fixes # (issue)

Adds # (feature)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you make sure to update the documentation with your changes? E.g. record bug fixes or new features in What's New. Here are the
  documentation guidelines
• Did you build and run the code without any errors?
• Did you report the running environment (NPU type/MS version) and performance in the doc? (better record it for data loading, model inference, or training tasks)
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@xxx

[gemini-code-assist]

Summary of Changes

Hello @SamitHuang, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request updates the README.md file to reflect the latest developments and capabilities of the mindone project. It incorporates recent news regarding model and library upgrades, streamlines installation guidance, and refreshes the featured diffusion model example. Additionally, it expands the list of officially supported models and updates compatibility details, ensuring the documentation accurately represents the current state of the project.

Highlights

• News Section Update: A new entry has been added to the news section, announcing the upgrade of diffusers to v0.33.1 and transformers to v4.50.1, along with support for new generative models including QwenImage, FluxKontext, Wan2.2, and OmniGen2.
• Installation Instructions: The recommended installation method has been updated to suggest installing the latest version from the master branch based on MindSpore 2.6.0, removing the previous v0.3.0 specific instruction.
• Diffusion Model Example: The example code for diffusion models has been switched from Stable Diffusion 3 to Flux Kontext, showcasing a more recent and advanced model with an updated code snippet and image reference.
• Compatibility and Supported Models: Compatibility information has been updated to MindSpore 2.6.0 and hf diffusers 0.33.1. The count of supported pipelines has increased from 160+ to 240+, and the table of supported models under mindone/examples now includes QwenImage, FluxKontext, Wan2.2, and OmniGen2.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates the README file with the latest news, installation instructions, and a new quick tour example featuring Flux Kontext. It also expands the list of supported models. My review focuses on improving the clarity and correctness of the documentation by pointing out several typos and inconsistencies in model naming. Addressing these points will enhance the readability and professionalism of the project's main page.

[gemini-code-assist]

There are a few typos and inconsistencies in the new announcement. For better readability and consistency, "FluxKontext" should be "Flux Kontext", "Wan2.2" should be "Wan 2.2", and "OmniGen2" should be "OmniGen 2".

Suggested change

	- [2025.09.15] We upgrade diffusers to v0.33.1 and transformers to v4.50.1 based on MindSpore. QwenImage, FluxKontext, Wan2.2, OmniGen2 and more than 20 generative models are now supported.
	- [2025.09.15] We upgrade diffusers to v0.33.1 and transformers to v4.50.1 based on MindSpore. QwenImage, Flux Kontext, Wan 2.2, OmniGen 2 and more than 20 generative models are now supported.

[gemini-code-assist]

The alt text for the image has a typo. flux_kontext should be Flux Kontext for better accessibility and consistency.

Suggested change

	<img src="https://github.com/townwish4git/mindone/assets/143256262/8c25ae9a-67b1-436f-abf6-eca36738cd17" alt="flux_kontext" width="512" height="512">
	<img src="https://github.com/townwish4git/mindone/assets/143256262/8c25ae9a-67b1-436f-abf6-eca36738cd17" alt="Flux Kontext" width="512" height="512">

[gemini-code-assist]

There's a typo in the word "compatible".

Suggested change

	- compatibale with hf diffusers 0.33.1. diffusers 0.35 is under development.
	- compatible with hf diffusers 0.33.1. diffusers 0.35 is under development.

[gemini-code-assist]

There's a typo in the word "autoencoder".

Suggested change

	| [models](https://github.com/mindspore-lab/mindone/tree/master/mindone/diffusers/models) | support audoencoder & transformers base models same as hf diffusers 50+
	| [models](https://github.com/mindspore-lab/mindone/tree/master/mindone/diffusers/models) | support autoencoder & transformers base models same as hf diffusers 50+

[gemini-code-assist]

The model names in this table are inconsistent and could be improved for readability. For example, qwen_image could be Qwen Image, flux_kontext could be Flux Kontext, wan2_2 could be Wan 2.2, omni_gen could be OmniGen, and omni_gen2 could be OmniGen 2. This would make the table easier to read and consistent with how models are usually named.

Suggested change

	| Text/Image-to-Image | [qwen_image](https://github.com/mindspore-lab/mindone/pull/1288) 🔥🔥🔥 | ✅ | ✖️ | ✖️ | Alibaba |
	| Text/Image-to-Image | [flux_kontext](https://github.com/mindspore-lab/mindone/blob/master/docs/diffusers/api/pipelines/flux.md) 🔥🔥🔥 | ✅ | ✖️ | ✖️ | Black Forest Labs |
	| Text/Image/Speech-to-Video | [wan2_2](https://github.com/mindspore-lab/mindone/pull/1243) 🔥🔥🔥 | ✅ | ✖️ | ✖️ | Alibaba |
	| Text/Image-to-Image | [omni_gen](https://github.com/mindspore-lab/mindone/blob/master/examples/omnigen) 🔥🔥 | ✅ | ✅ | ✖️ | Vector Space Lab|
	| Text/Image-to-Image | [omni_gen2](https://github.com/mindspore-lab/mindone/blob/master/examples/omnigen2) 🔥🔥 | ✅ | ✖️ | ✖️ | Vector Space Lab |
	| Text/Image-to-Image | [Qwen Image](https://github.com/mindspore-lab/mindone/pull/1288) 🔥🔥🔥 | ✅ | ✖️ | ✖️ | Alibaba |
	| Text/Image-to-Image | [Flux Kontext](https://github.com/mindspore-lab/mindone/blob/master/docs/diffusers/api/pipelines/flux.md) 🔥🔥🔥 | ✅ | ✖️ | ✖️ | Black Forest Labs |
	| Text/Image/Speech-to-Video | [Wan 2.2](https://github.com/mindspore-lab/mindone/pull/1243) 🔥🔥🔥 | ✅ | ✖️ | ✖️ | Alibaba |
	| Text/Image-to-Image | [OmniGen](https://github.com/mindspore-lab/mindone/blob/master/examples/omnigen) 🔥🔥 | ✅ | ✅ | ✖️ | Vector Space Lab|
	| Text/Image-to-Image | [OmniGen 2](https://github.com/mindspore-lab/mindone/blob/master/examples/omnigen2) 🔥🔥 | ✅ | ✖️ | ✖️ | Vector Space Lab |

[SamitHuang]

Currently, it depends on these PR to be merged:
#1288
#1243

Need further update after #1299 merged