A very next step when playing around with generative AI tools, is to make a video from a given image. In my case I wanted to animate the above image of mysself (AI generated with Flux/LoRA) in a natural way to make me speak out.
My first try out where with RunwayML – unfortunately only Model #2, not the newer version 3. The results are not the great: the movement is not natural mostly weird and also the transition in the face (morphing) looks rather spooky. So this first try was failure.
Try #2 with minimax video
A very new image2video model is minimax. You can easy access it via fal.ai. The prompt was very simply, just instruct to make me speak out and show some natural gestures. The output is way better then the one from RunwayML. It looks smoother and more natural. I wouldn’t say it is truely realistic but it must be around 90% acurate.
In the previous post I explained how to train Flux/LoRA to create images of yourself. This is a quite straightforward process and after that we can create via prompts the images we want to. In my case I did my first try outs with some business portraits for myself. The results a good, sometimes a bit to blurry and smoothened out. But there is an issue that the Flux AI tends to add you at least a 2nd time into the picture if you place yourself into a typical scenery with more then just 1 person. I also found a simple solution to overcome this. Here are my example prompts and the outcomes:
Professional business portrait of erich wearing a dark grey suite, sitting confidently at a modern office desk. Background shows a contemporary office with glass windows and city views. Well-lit with soft, natural light, highlighting a friendly, approachable smile, wearing a formal suit.
Professional business portrait of erich, standing in a modern office meeting room with a table and screen in the background. Wearing business attire with a confident, relaxed posture, arms crossed and smiling warmly. Soft, professional lighting enhances a welcoming expression.
Professional portrait of erich, seated behind a modern executive desk, surrounded by minimalistic office decor like a laptop, notebook, and pen holder. Well-lit room with large windows and subtle artwork in the background. Dressed in a formal suit or business casual, with a focused, thoughtful expression.
Professional yet relaxed business portrait of erich, standing in a collaborative office space with colleagues visible in the background, blurred slightly. Wearing business casual attire, arms relaxed, with a warm, approachable expression. Modern office setting with plants and glass walls, lit with natural light.
Here we have the case, that I have been put a 2nd time into the picture.
Professional business portrait of erich, caught in a natural conversation with a colleague in a modern office lounge area. Wearing business attire, seated on a stylish office sofa with hands gesturing slightly as if explaining something. Background features office decor with plants, well-lit with ambient lighting.
How to overcome the multiple images of yourself in scenes
This is actually quite simple, you just need to tell the AI via prompt that only one person is yourself and the others should be given random faces:
erich is sitting in a high class restaurant and having dinner with a lovely woman wearing an elegant black dress. erich is smiling into the camera. he is wearing smart casual clothings. in the background we see the typical scenery of a restaurant with tables, people etc. only the person sitting on the table with the woman is erich. add random faces to all the others
The first AI apps on the mobile I remember were some fun apps creating from an given image of you, different scenario pictures like a funny background. The makers charged quite some money for like 5 custom images. However with Flux LoRA there is a even better outcome for less money possible.
Flux is the image generator model by German AI company Black-Forest-Labs and is at the moment the hottest and best image generator for photo realistic images. The image generator itself can be easily for free on their website.
To achieve custom pictures of us we need to go a step further and train the model. This is not complicated and cost only 2$. I use the AI workspace fal.ai for this where you can work with many different model – and also Flux and Flux SoRA.
You will see the form pictured above. Add face shots, selfies, close up pictures of you into the uploader. I used about 25 pictures of me. Then select a “Trigger Word” – to reference the training data in your future prompt. I simply use my name “Erich” as the trigger word. Then let the training start – it will last around 1 minute to finish.
Step 2: Run the model with your trigger word
To create an image prompt based on the trained data with the Flux SoRA model simply klick on the Run button of the training form:
Enter your prompt referencing the “Trigger word” you have set before and let the magic happen. I generated some examples using very simple 1 line prompts:
The business picture is really great and it looks very much like me when in use in small scale. When getting closer you can see blurry areas somehow. The 2nd picture was to put me to Oktoberfest with interesting result being put twice into the picture 🙂 The black t-shirt and the yellow backbag is actually taken from one of my training pictures. Overall I am quite happy with the outcomes and with some more detailed prompts, you definitely will get even better results. Total costs ~2$.
Advanced prompt examples
Here are some more examples I generated today with a more advanced promoting:
erich is captured mid-speech. His expressive face, adorned with a salt-and-pepper beard and mustache, is animated as he gestures with his left hand. He is holding a black microphone in his right hand, speaking passionately. The man is wearing a dark, textured shirt with unique, slightly shimmering patterns, and a green lanyard with multiple badges and logos hanging around his neck. The lanyard features the "Autodesk" and "V-Ray" logos prominently. Behind him, there is a blurred background with a white banner containing logos and text, indicating a professional or conference setting. The overall scene is vibrant and dynamic, capturing the energy of a live presentation.
This is a summary of my progress with AI image generators over the past months. From first try outs with creating new movie posters to very advanced prompting showing really cool results.
Alternative movie posters
Those are my first try-outs with AI image generators and also already over 1 year old. I used Dall-E for the generating (except the 2 alien pic – those came from Flux. Dall-E still has huge problems putting text 1:1 into the image, as you can clearly see. Flux is comparable great at this task.
Comic strips
Pixel Art
Advanced prompting results
This are the my best images and most advanced prompts I have been using in the past. Most images are generated with Dall-E 3 and Flux1.0. The more realistic looking image have been generated with flux, which as at the moment for me the reference when it comes to image generating. If you need not the super realistic look, Dall-E will also do. Plus: those 2 you can still be used for free.
Simple AI tools and the connection of them makes it very easy to create large amounts of content (here in the example text) for your blog, website etc. All tools I used here are free and easy to handle.
Step 1: ask chatgpt to create a list of popular items of any category you are interest in. In my example I asked it for the most popular DOS Games with some data of additional information:
Chatgpt will return you a handy table that you can easily further process. The data is nice, but we need some more text and therefore we are going to query chatgpt for each of the game for a summary. You can do this also in the normal prompt screen, but this would take very long. I am using for this a Google Sheet with the GTP for work plugin, that allows you to use the chatgpt als normal Google Sheet functions.
Step 2: Add some more content in a Google Sheet. When you copy/paste the table it will look something like this:
I already added another column Summary where then we want chatgpt to generate our text for each game. To do that we use a simple function:
After some time the request will be filled with a text comparably to mine:
You can add the details or specifics you want to have in your text. Quick hint on the prompt: chatgpt tends to just end longer texts in the middle of a sentence, so to trick it here tell in the prompt you want a 1.500 word summary and the only the first 750 words should be displayed. With this little tweak you will avoid having cut off texts.
As we are in a Google Sheet, the only thing we have to do now is to extend the function to all other rows below and let chatgpt produce the 100 texts. Having our complete texts we can go the next step and get the data into our wordpress Blog. Doing so we use zapier.
Step 3: Import the data als new content to your wordpress blog. Create a new transfer with your source “Google Sheets” and destination “WordPress Blog”.
In the next step choose the Google Sheet File from the dropdown:
Your WordPress also needs some preparation and you need to install the zapier plugin there, so that the app can communicate properly with the blog system:
Next we need to connect our WordPress blog and enter the credentials:
And then we can put everything together and tell zapier which data to use from the Sheet to create our new blog post (you can also create pages or attachments with images):
You can also use HTML in some fields like the Content to create more advanced entries. For the game example here we could create a little table at the top showing all the additional data we have. In the next step you can then review the full dataset and choose which one zapier should transfer.
Final result: the post in WordPress:
If you have chosen the full 100 dataset you will have 100 new posts in your blog. Some constraints from the zapier/Wordpress connection: As you can also see in the screenshot the plugin uses the old classic editor and not the new block editor. Also there are no links in the posts, which are to add in another step.
To fully automate the flow, create a new Zap from the transfer in zapier and let the process run each time a new row has been added to the Sheet. So all you have to do then, is add the row with the name of a new game and the chatgpt function will create your text and the zapier zap will import it automatically to your blog.
We use cookies to ensure that we give you the best experience on our website. If you continue to use this site we will assume that you are happy with it.
