A version was released before, but it was for temporary use. Taking this opportunity to release the first MOSS-image T2I LoRA today, I have optimized the workflow. As usual, here is what it looks like.

There are five sections in total.

Load the image. This workflow can reverse-engineer prompts from the image.

Used to control the aspect ratio/size of the generated image

Used to control the random seed

The core of T2I, where you can enter prompts or adjust the basic parameters of ksample

Display the generation results

Here the focus is on 4: the core of T2I. This is what it looks like when expanded.

It consists of two parts: the upper part is for prompt generation, which can generate prompts suitable for MI based on input images or texts. The lower part is the core generation area of MI. It is a basic workflow. Notably, I have equipped it with two LoRAs, which will greatly boost your generation speed and quality. The LoRA links are in the notes.

OK! That's all! I hope you like it!

If you like my sharing and want to get more content and resources related to AI image generation, welcome to join my private community.👇👇👇

NO8D-AI-Workshop

🫡May the AI-power be with you, see you soon!🫡

Disclaimer: My model or workflow is solely for learning and communication purposes and shall not be used for any commercial activities. All responsibilities for the generated content, including its legality, ethical implications, or potential misuse, are borne entirely by the user. By using this model or workflow, you agree to this principle. Please use it responsibly within the scope of local laws.