@Dare Akoms Thank you so much, I really appreciate it! 🥰 And thanks for pointing out the gloves. The client for this video is targeting a US audience, so your comment is very helpful. I’ll regenerate the burger and plating shots with gloves. Happy to share the workflow. This video is part of a larger project for a food blogger. I handle the visual generation for the project in cases where professional filming isn’t possible. 1. I usually start with a text recipe, imagine the final dish and preparation stages, and generate images in Midjourney v7. Since I need consistent angles, lighting, background and tableware, I trained a GPT assistant that standardizes my prompts, so creating them now takes just a few seconds. I also use Midjourney personalization for this project to keep a consistent visual style. 2. After selecting the best image, I upscale it (sometimes directly in Midjourney v5 because it has 4x upscale, sometimes in Topaz AI for batch processing). Occasionally I refine small details in Photoshop. 3. For animation I used Runway Gen 4.5. The animation prompt is very simple, mostly camera movement and object motion. 4. When all shots are ready, I assemble everything in CapCut, add sound effects and music (I attached a screenshot of the timeline so you can see how it looks). I usually find sounds in libraries, and sometimes generate music in Suno. And that’s basically how the video comes together 🙂

@Jane Kott Thanks! Likewise 😊

Hi Sabina! Just followed you on Instagram. Good luck on Upwork! 😘

Hi Victoria 👋

Same experience here. When the tone really matters, I usually go with video first and then add the voice in ElevenLabs. The control over the voice and pacing there works much better for me

Creator. One of Ania’s courses actually opened the door to the AI creative world for me, and it became one of my favorite income streams 😊