Fresh out of the oven
These tools are new, so the odd thing may still wobble. If something looks wrong, it probably is. Tell us and we will sort it.
Fresh out of the oven
These tools are new, so the odd thing may still wobble. If something looks wrong, it probably is. Tell us and we will sort it.
Fresh out of the oven
These tools are new, so the odd thing may still wobble. If something looks wrong, it probably is. Tell us and we will sort it.
Pinnora's AI thumbnail maker has six controls. What the video is about is the required brief: the topic plus the one reason someone would tap it. Text overlay takes up to 40 characters, and that line is what the model is told to draw. Leave it empty and a hook pass writes a two to five word line first, reading your brief and your project's pains and desires. Style picks between Bold text, Product hero, Lifestyle, Comparison and Before / after. Face emotion runs from No face through Surprised, Skeptical, Confident, Amused and Concerned. Variations goes up to 12, each one a separate render on its own angle. Model sits on Auto, which is openai/gpt-image-2, and every render is 16:9.
The tool is open above. This is the short version of what to do with it.
What the video is about is the required brief: the subject and the one reason someone would tap it. Fill for me opens the Prompt Builder, which drafts that line from the playbooks and your project's grounding and preselects the dials below. Cmd or Ctrl plus Enter starts the run from the box.
Text overlay caps at 40 characters and asks for 4 to 6 words. That line is handed to the model as the text to draw exactly. Leave the box empty and the hook pass writes a two to five word line from your brief and your project's pains instead.
Under Look and expression, Style offers Bold text, Product hero, Lifestyle, Comparison and Before / after. Comparison and Before / after send split-frame direction, Lifestyle asks for a person mid-reaction, Product hero puts the product mid-use. Face emotion sets that person's expression, or No face.
Variations sits under Volume, runs 1 to 12 and starts at 3, so the button reads Generate 3. Each one is a separate render carrying its own angle. Leave Model on Auto for openai/gpt-image-2. Results land in the right pane and stay under History.
Short answers to what people ask before they start.
Pick the right image type for the job, and get product shots that look photographed rather than rendered.
The rest of the family. Every one is free to try and runs on the same engine.
