PS+AI drawing is completed in one step, and the effect is amazing! Adobe Firefly 2 major update: comprehensive model upgrade, perfect support for vector graphics

Adobe’s AIGC mapping platform Firefly recently underwent a major update. Adobe named it Firefly 2 directly.

First of all, the image model quality of Firefly image 2 has made huge progress

The new one on the right You can even see the wrinkles of marshmallows in the model picture

In the new model on the right, the details of bird feathers and depth of field are better than The first generation model is much better

Firefly Image 2 model is able to produce significantly higher quality images, especially when it comes to rendering realistic human bodies involving foliage, skin textures, hair, hands and High-frequency details such as facial features. The images generated using the Firefly Image 2 model have higher resolution, more vivid colors and higher color contrast

and also add the function of generating vector images, which can be directly displayed through the prompt Generate vector graphics

##Adobe has also added several new features that can greatly improve the user experience:

Generate matching: Based on the sample image uploaded by the user, generate an image with a similar style

Image settings: You can make detailed adjustments to the generated image , including depth of field control, motion blur, field of view adjustment and generation Better express your needs, thereby obtaining more ideal image output

More capable image models, comprehensively improve the quality of generated images

Adobe claims that Firefly 2 has greatly improved the quality of image output, especially in aspects such as leaves, skin textures and facial features, with more realistic and fine details compared to the previous generation model.

Especially for portrait images, the human body rendering quality is enhanced by improving skin, hair, eyes, hands and body structure, providing better colors and more accurate dynamic effects.

The character skin generated by the new model on the right is more realistic and natural, and the depth of field effect of the background is also more obvious.

In the picture on the left, the light and shadow effects of the characters in the new model are more realistic and consistent, and the background details are more natural. The cloud details in the middle picture are more natural and rich, and the light and shadow are softer. The details of the characters on the right are more realistic, and the hand depictions are more natural. The marshmallow effect is more realistic and detailed.

From the picture content, it is obvious that the new model has a more accurate understanding and depiction of what a CRT monitor is and what a TV is. The previous generation engine basically only drew a display screen, while the new generation engine draws the details of the display more reasonably.

From the perspective of picture style, the picture style generated by the new model has more natural light and shadow, more realistic, and more consistent tones.

Like several other image-generating AIs, Firefly can also freely choose the model version of the image-generating model. Although version 2 is theoretically better than version 1, if users want to use version 1 to generate pictures, there is no problem at all.

Tested 3 new functions, giving users the ability to finely control images

The changes in the image model are Firefly’s output of the model " "Major improvement in overall quality"

But what users value most about image-generating AI products is the ability to control the image generation process. Adobe's decades of accumulation in these aspects are obviously not comparable to Midjourney, a newbie in image products, DALL-E 3.

We have also conducted a series of actual tests for the three functions of generating matching, image settings and prompt suggestions in this update

The biggest feeling after using it is that the combination of PS AI drawing is so cool!

First of all, register through Firefly’s official website to use all these features.

Entrance address: https://firefly.adobe.com/inspire/images

Generate Matching function:

Similar to the "style converter" function of other image-generating AIs, the generation matching function can generate highly similar styles and content based on a picture given by the user. Sexy pictures can be understood as Adobe’s version of the “image to image” function.

For example, when we want to create an eye image based on the pencil sketch style, we only need to provide a sketch of the same style, and then enter a prompt, such as "a person's eyes".

Firefly 2 then generates four sketch pencil style images that perfectly match our desired style

Use the "neon theme" picture and the puppy prompt word to generate "neon puppy".

Use the original picture in the paper-cut style and match the cat’s prompt words to generate a paper-cut style cat.

In addition, you can also adjust the style of the image according to your personal preferences, transforming it into a vivid three-dimensional style, giving the image a more vivid and engaging Traits.

According to the requirements of different projects or the diversity of personal creativity, this feature allows you to easily customize and create unique images

Image settings

In addition, Firefly also provides the function of secondary editing of the generated images, which is equivalent to integrating the ability of PS AI to generate images. , provides a very convenient workflow for users who have high requirements for picture details.

For example, you can use the image of a paper-cut kitten just generated by the system and edit this material at any time, including adding text, graphics or other elements.

This flexibility allows you to further personalize and refine the generated content as needed, creating images that match your unique creativity and meet your specific needs.

This function provides users with more choices and control, especially in terms of creativity and customization

In addition, for Visual intensity, color tint, lighting, composition can all be further modified. For example, based on the generated cat image, the tone, lighting and other effects can be changed in the lower right corner.

If you want to spawn a golden kitten, you can choose among Firefly 2’s color and tint options

#You can also combine more elements in your creation, such as scenes shot through windows.

Prompt word suggestion

As the biggest bottleneck on the human side of AI drawing-prompt word, Adobe This update also provides its own solution.

When the user's input prompt is too short or cannot clearly describe the user's needs, the system will provide the function of prompt word suggestions

For example, When we enter a short prompt like "a woman is on top of the mountain during sunset", the system will automatically generate five different sentences. These sentences will present a variety of ways to express similar situations for us. Choose and further refine our creative needs.

This function allows us to customize and expand our creative ideas more flexibly, increasing the possibility and diversity of creativity.

Firefly 2 released by Adobe shows more powerful performance, and these aspects jointly reflect its advantages. It not only improves image quality, but also introduces vector image generation capabilities and adds a number of new features, greatly improving the user experience and providing excellent tools for creators and designers

The above is the detailed content of PS+AI drawing is completed in one step, and the effect is amazing! Adobe Firefly 2 major update: comprehensive model upgrade, perfect support for vector graphics. For more information, please follow other related articles on the PHP Chinese website!