> For the complete documentation index, see [llms.txt](https://docs.seaart.ai/guide-1/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.seaart.ai/guide-1/getting-started/beginner-guide.md). # Beginner Guide Create your first image from a short prompt, check the result, and save a copy. This guide uses Text to Image so you can begin without a reference image, LoRA, or custom workflow. ## Before you begin * Sign in to [SeaArt AI](https://www.seaart.ai/). * Choose one simple subject you want to create. For your first attempt, use one subject and keep the model's default settings. You can explore advanced controls after you have a result to compare. ## 1. Open the AI Image Generator Open SeaArt's [AI Image Generator](https://www.seaart.ai/create/image) and enter a description of the image you want to create in the prompt box.
AI Image Generator
## 2. Choose a Model Browse the available models and their example images. Pick one that matches your goal, such as a realistic photo or an illustration.
Choose a Model
Keep the default settings for your first attempt. You can explore other options once you have a result to compare. ## 3. Write Your First Prompt A simple prompt can include four elements: **Subject + Setting + Style + Lighting** For example: *A small orange cat sitting beside a window in a cozy room with houseplants, watercolor illustration, soft morning light.* This prompt tells the model what to create, where the scene takes place, what style to use, and how the scene should be lit. You can use the same structure for other ideas by changing the subject, setting, or style. Start with a clear description before experimenting with advanced options. For more advanced techniques, see the [Advanced Guide](/guide-1/advanced-guide.md) for topics such as LoRA training and ComfyUI workflows. ## 4. Generate Your Image Review your prompt and selected model, check the displayed generation cost, and click the generate control.
Generate Your Image on SeaArt AI
Wait for the task to finish, then open the result. Generation time varies, so check the task status if it is still processing. ## 5. Review and Improve Your Image Compare the result with your original idea: * Is the main subject recognizable? * Does the setting match your prompt? * Is the visual style correct? * Are there any distracting details or obvious defects? If something needs improvement, change one element at a time. For example, replace “watercolor illustration” with “colored pencil illustration” to try a different style, or add “the entire cat is visible” to clarify the framing. If you want to change only part of an image while keeping the rest, explore the relevant image-editing guide. ## 6. Save Your Creation Open the completed image and use the download control to save it to your device. If you cannot find the file, check your browser's downloads. To find your creations later, open your personal page and go to the Works section. Make sure you are signed in to the account you used to generate the image. Downloading an image and publishing a work are different actions. Check the available visibility settings before sharing your creation. ## What If Your Generation Fails? If generation fails, check the task status and any error message before trying again. If the problem persists, contact SeaArt support with the task ID, model name, error message, approximate time, and a screenshot if available. Resource deductions and refunds depend on the current site rules, so check the applicable policy rather than assuming a failed task will be refunded. For more help, visit [SeaArt's FAQ](/guide-1/faq.md) or [support page](/guide-1/getting-started/page-introduction.md#community-and-support).