AI Personal Learning
and practical guidance
Beanbag Marscode1

Awen: using voice to manipulate image creation and modification

General Introduction

Awen is an innovative generative AI platform designed to help users quickly create and edit images and video content through voice and text commands. Users simply describe their needs, such as "Draw a Swiss mountain lake, add a boat, and turn it into a sunset scene," and Awen intelligently understands the intent and generates the corresponding visual work. Built by a team that combines machine learning, software engineering, and creative production experience, it aims to simplify the complexity of traditional design tools. Currently in beta, users can join the waiting list via the website to experience a tool that redefines the creative process. Whether you're a professional designer or a novice, Awen makes it easy to bring your ideas to life.

Awen: create and edit images and videos using your voice-1


 

Function List

  • Generate images from voice commands: Generate images that match the user's intent through natural language descriptions.
  • Real-time image editing: Support for modifying image details with voice or text, such as adjusting the scene, lighting, or adding elements.
  • Video animation generation: Converts still images into moving video, e.g. animating objects in a scene.
  • multimodal operation: Combines voice and text input to provide flexibility.
  • Creative Intent Understanding: Utilizing AI reasoning technology to accurately capture the creative needs in user descriptions.
  • Cross-industry applicability: Support for creative production in advertising, fashion, media, publishing, etc.

 

Using Help

How to get started with Awen

Awen is currently in beta and is not yet fully open for public use. To experience this tool, you need to visit the official website https://www.awen.ai/ and then follow the steps below:

  1. Sign up for the waiting list::
    • Open the homepage of the website and find the "Join the Waitlist" button.
    • Once clicked, enter your email address and submit the application.
    • Upon successful submission, you will receive a confirmation email that you have been added to the waiting list.
    • Wait for official notification. Once a beta slot opens up, the Awen team will contact you via email to provide access or further guidance.
  2. Gain access::
    • Invitation codes or specific links may be required during the testing phase, depending on official arrangements.
    • Once you have received the invitation, follow the link or instructions in the email to access the Awen interface.

Since Awen is a cloud-based online tool, there is no need to download or install any software; all that is required is a device that supports voice input (e.g., a computer or cell phone with a microphone) and a stable Internet connection.

Main function operation flow

Here are the core features of Awen and their detailed usage to help you get started quickly:

1. Using speech to generate images

  • procedure::
    1. Once you are in the Awen interface, click on the microphone icon or select "Voice Input" mode.
    2. Speak clearly into the microphone and say what you want, e.g., "Draw a Swiss mountain lake surrounded by snow-capped mountains and pine trees."
    3. Upon releasing the microphone button, Awen immediately processes your commands, generating an initial image within seconds.
    4. Once the image is generated, the screen displays the results, which you can view and decide if further adjustments are needed.
  • caveat::
    • Ensure a quiet environment to avoid background noise interfering with speech recognition.
    • Described in simple, natural language, the AI generates content based on keywords.
  • typical example::
    • Enter: "Draw a tropical beach with palm trees and a blue sky."
    • Output: an image containing a sandy beach, palm trees and a clear sky.

2. Real-time image editing

  • procedure::
    1. Click the "Edit" button on the resulting image or continue adjusting it directly by voice.
    2. Say modification commands, such as, "Make the sky the color of sunset and add a boat."
    3. Awen updates the image in real time to show the modified effect.
    4. If you are not satisfied with the results, you can repeatedly enter new commands until you achieve the desired result.
  • Advanced Techniques::
    • Details can be specified, such as "the boat is red" or "the sky has an orange and purple gradient".
    • Support undo function, if a change is not satisfactory, you can say "undo previous step".
  • typical example::
    • Original photo: Swiss Mountain Lake.
    • Enter: "Turn the lake green and add a flying bird."
    • OUTPUT: The lake turns green and a bird appears in the sky.

3. Generation of animated videos

  • procedure::
    1. After you have finished editing the image, select the "Animation" option.
    2. Describe the animation effect in voice, e.g., "Make the boat move across the lake and the clouds float in the sky."
    3. Awen generates a short video based on the description, usually a few seconds to a dozen seconds in length.
    4. Once generated, you can preview the video and choose to download or continue tweaking.
  • caveat::
    • Animation effects are based on image content and are described as relevant as possible to existing elements.
    • Complex animations may take longer to generate.
  • typical example::
    • Enter: "Let the birds fly through the sky and the lake ripple."
    • Output: an animation of a bird in flight with ripples on a lake.

4. Text input mode

  • procedure::
    1. If it is not convenient to use voice, you can switch to the "Text Input" mode.
    2. Enter a description in the text box, e.g., "Create a future city night scene with flying cars and tall buildings."
    3. Click the "Generate" button and Awen will generate an image or video based on the text.
  • Applicable Scenarios::
    • Ideal for quiet environments or scenes that require precise descriptions.

Functional Operation Tips and Suggestions

  • articulate: Try to use specific nouns and simple sentences to avoid vague descriptions, both in speech and in text. For example, it is easier to generate accurate results by saying "draw a white horse running in the meadow" than "draw a beautiful scene".
  • step by step operation: Complex ideas can be done in steps, first generating a base image and then gradually adding details.
  • Preview and Adjustment: Double-check the details after each generation and revise them whenever you are not satisfied.
  • Equipment Requirements::
    • It is recommended to use a device equipped with a high-quality microphone to ensure accurate voice recognition.
    • We recommend using the latest version of Chrome or Firefox to maintain a stable network.

Featured Functions

Creative Intent Understanding

The core highlight of Awen is that its AI can deeply understand the user's creative needs. For example, when you say "draw a dream forest", it will not only generate trees, but may also automatically add fog, light and shadow and other dream elements. This intelligent reasoning sets it apart from traditional tools by eliminating the need for users to manually adjust complex parameters.

Multimodal Flexibility

The use of voice and text together is very flexible. For example, you can generate a diagram with voice and fine-tune the details with text. This dual-input mode is particularly suited to team collaboration or rapid iteration of ideas.

Cross-industry applications

Awen is designed to work in a variety of scenarios:

  • advertising design: Quickly generate promotional graphics or animations.
  • fashion industry: Create an inspiration sketch or presentation video.
  • media production: To illustrate an article or video content.

Frequently Asked Questions

  • Is the generated content commercially available?
    Awen is currently in beta and commercial access is subject to the terms and conditions posted on the website.
  • Does it support Chinese voice?
    It has not been officially clarified, but the testing phase is likely to be predominantly in English, and it is recommended that descriptions be in English for best results.
  • How fast is it generated?
    Depending on the network and description complexity, it usually ranges from a few seconds to tens of seconds.

With the above steps and tips, you can easily get started with Awen, quickly turn creative ideas into images or videos, and enjoy the convenience and fun of AI!

CDN1
May not be reproduced without permission:Chief AI Sharing Circle " Awen: using voice to manipulate image creation and modification

Chief AI Sharing Circle

Chief AI Sharing Circle specializes in AI learning, providing comprehensive AI learning content, AI tools and hands-on guidance. Our goal is to help users master AI technology and explore the unlimited potential of AI together through high-quality content and practical experience sharing. Whether you are an AI beginner or a senior expert, this is the ideal place for you to gain knowledge, improve your skills and realize innovation.

Contact Us
en_USEnglish