How to generate an image from deepseek

- Since it cannot run on the default portal, we need to run this model manually on the virtual machine or locally on the computer.
- If you don’t want the hassle of running Janus-Pro-7b models manually on a virtual machine, then you can use this free tool DeepSeek Image Generator.
- If you are a fan of wanting the best results, then running DeepSeek locally on your computer, the Janus-Pro-7b model is a great solution.
China’s DeepSeek has become a fierce competitor to Openai’s Chatgpt and Google’s Gemini AI Chatbots, and has even improved them in an open source way. The tool also supports image generation through its Janus-Pro-7b model, but is not available in default applications and websites. Recently, we explored the method to run DeepSeek locally on your computer, which unlocks the full potential of its high-level large language model without any limitations. In this guide, let’s learn how to generate images using DeepSeek for free.
Create an image from a text prompt in deepseek
Image generation only supports Janus-Pro-7b llm by deepseek. Since it cannot run on the default portal, we need to run this model manually on the virtual machine or locally on the computer. Both methods are free to use.
For comparison, Chatgpt uses its GPT-4O image model, while Gemini uses Imagen 3 for image generation. Both tools provide a limited number of image creation requests in the free tier, but DeepSeek is open source and there is no such limitation. Therefore, DeepSeek already has an advantage over Chatgpt and Gemini. Let’s see how we can use it to make an image from a text prompt.
Running Janus-Pro-7b on a hug face
Hug face is a powerful tool that allows you to run large language models and perform complex simulation operations. Just like a virtual machine, where you can access advanced GPU resources for testing. The free version is enough to let us run DeepSeek’s Janus-Pro-7b model to generate images using the following simple steps:
1. Open the DeepSeek AI space on the hug face.
2. Make sure you choose the Janus-Pro-7b model.
3. Click Text to image generation.

4. Enter a text prompt and describe the image you want to create. Image quality is better when you describe the image quality in detail. When finished, click Generate an image.
5. DeepSeek will generate up to four images according to your requirements. You can choose the best one and save it on your device.

By default, DeepSeek generates images at a 1:1 aspect ratio of 512×512 resolution. It does support higher resolutions, but depends on the load on the hug-face server. Here are some results we generated using DeepSeek.



Using DeepSeek Image Generator
If you don’t want the hassle of running Janus-Pro-7b models manually on a virtual machine, then you can use this free tool DeepSeek Image Generator. It has an easy-to-use interface where you can enter prompts directly and get AI-generated images. You can use it for free:
1. Go to DeepSeekimageGenerator.in. If you are using a website you may ask you to disable ad barriers. Click Start creating now.

2. Enter a text prompt to get the desired image. You can also provide negative tips and instruct the tool to avoid certain elements.
3. Select the number of images you want and the resolution you want. The maximum supported resolution is 1024×1024.

4. Click Generate an image.
The tool will generate images using DeepSeek within one minute. It allows you to create 100 images per hour. Here are some samples we generated:


Run DeepSeek locally on your computer
If you are a fan of wanting the best results, then running DeepSeek locally on your computer, the Janus-Pro-7b model is a great solution. This can be done by downloading the model from DeepSeek’s website and running the model on the system using Ollama. We’ve demonstrated this guide on Windows computers, but you can do this on MacOS and Linux as well. Here are the steps:
1. Download and install Ollama on your computer.
2. Open the command prompt and enter ollama run erwan2/DeepSeek-Janus-Pro-7B
.

3. Ollama will first download the Janus-Pro-7b model on computer size 4.2GB. This is a one-time process that can take up to 5 minutes depending on your internet speed.
4. After completion, enter a prompt and ask DeepSeek to generate an image. For example, “produces an image of a forest where dense trees flow in between, and birds fly in the sky.”
5. Ollama and DeepSeek will use the computer’s CPU, GPU, and other local resources to generate images. Once done, you can view and save it on your system.
FAQ
Q: Can I generate images in DeepSeek for free?
You can generate images in DeepSeek using the Janus-Pro-7b model, but it needs to be run manually on the virtual machine or locally on the computer.
Q: Does DeepSeek support video generation?
Currently, DeepSeek does not support video generation. It is limited to text and image responses only.
Q: Is DeepSeek better than Chatgpt when generating images?
Compared to ChatGpt, DeepSeek does not have custom image styles and lacks advanced features. Therefore, Chatgpt generates images better.
Summarize
DeepSeek’s Janus-Pro-7b model is one of the best ways to generate images for free. If you have a computer with a powerful GPU, you can run it locally on your system using Ollama, which you can use the tool even without Internet access. This is an excellent alternative to Chatgpt and Gemini, which have strict restrictions on image creation of free layers.
You may also want to read:
You can also follow us for instant tech news Google News Or comments about tips and tricks, smartphones and gadgets, please join Gadgetstouse Telegram Groupor subscribe Gadgetstouse YouTube Channel About the latest review video.
Was this article helpful?
YesNo