One full-body photo is enough: you, sitting on a trunk over an autumn lake with wired earphones in. 38 credits for both, flaws shown.
Real workflow: a bearded man in a mustard sweater and light jeans on a park path, then the same man sitting on a mossy trunk over a misty lake with white earphones in, and seen from his soles with his eyes closed. In the second picture, his reflection in the water does not match the trunk's.
At a glance
The Autumn Lake Daydream starts from a single full-body photo: you sit on a tree trunk over a calm lake in autumn, wired earphones in, miles away. The videosi.io tracker has listed it since 3 November 2026 with the "Just starting" status (page updated on 11 November), and media.io has a video generator page for it. The version going around is a video where the camera moves up from the shoes to the face. This template makes the two still photos.
You get two pictures. In the first, you sit on a mossy trunk, feet hanging over the water, facing the camera, with the mist and the orange trees mirrored in the lake. In the second, your soles take the foreground and your eyes are closed, head tilted. On the demo, the face and the outfit are faithful in both. The trunk rises diagonally in the first, and in the second the man's reflection in the water lands far too low.
For another mood built from your face, see the underwater portrait or the broken heart photo. To turn an existing photo from summer to autumn without changing the setting, use the season changer. Both renders cost 38 credits, see pricing.
These are the files of the workflow above, exactly as the models produced them, unretouched. The starting point is shown when there is one.
Starting point
Render
People who want to try the Autumn Lake Daydream trend on their own photo for a story, an Instagram or TikTok post, creators looking for a calm autumn picture to go with a playlist or a post.
A sharp full-body photo of you or of someone who agrees, ideally standing and facing the camera with the shoes visible, and a description of their outfit in the prompt (top, trousers or dress, shoes). The photo is optional.
Take a full-body photo of yourself
The model copies your outfit down to the shoes, and the second picture is framed on your soles. A sharp photo, standing, facing the camera, with your feet in the frame gives it everything it needs.
Describe your outfit in the prompts
The prompts describe a mustard yellow sweater, light blue jeans and white sneakers. Put in your coat, your dress or your boots instead, or the model may dress you like the man in the demo.
Keep the waterside or change it
The trunk over the lake is what makes the trend, but a wooden jetty or a rock at the water's edge works too. Change the start of the prompt and keep the wired earphones, the mist and the autumn trees.
Check the reflection before you post
On the demo, the shoes shot shows a reflection of the man that does not follow the trunk's. Zoom in on the bottom of the picture, and rerun that render for 19 credits if the reflection bothers you.
The same canvas, tuned for different needs: each variation is two or three lines of prompt away.
Change "the man" to "the woman" or "the couple" and describe each person and their outfit in the prompt. With two people, say whether you sit side by side on the trunk and whether you share one pair of earphones, or the model picks for you. Not tested on the demo.
Keep the autumn lake, the mist and the earphones, but change the seat: the end of a wooden jetty, a big flat rock, a moored rowing boat. One element per picture keeps the scene easy to read. Not tested.
On the demo, the trunk crosses the frame diagonally. Add "the trunk lying horizontal, parallel to the surface, a short distance above the water" to get closer to the pose in the trend's videos. Not tested.
On the demo, the camera stayed level with the trunk. Write "camera at water level, clearly lower than the soles, face at the very top of the frame", and add "reflection consistent with the trunk" or "no reflection of the person" to avoid the reflection that lands too low. Not tested.
Start from the shoes picture and plug in a Video node: describe a camera moving slowly up from the soles to the face, the mist barely moving and a leaf landing on the water. The template does not do this, we did not test it, and it is paid separately.
Replace golden hour with "early autumn morning, bluish light, thick mist on the lake, trees still orange". The picture gets calmer and less warm, but the model may dull the sweater's colour too. Not tested.
With a plain selfie, the model has neither your trousers nor your shoes, so it invents them. The second picture is built around the soles: without a full-body photo, they are no longer yours.
The demo prompts name a mustard sweater, light blue jeans and white sneakers. If you wear something else and do not say so, the model may mix your outfit with the demo's.
On the demo, the man's reflection shows under the trunk without following the trunk's reflection, and his reflected head ends up at the very bottom. It shows on a big screen. Look at the bottom of the picture before you post, and rerun if needed.
No. On the demo, the man has nothing in his ears, and the model added the white earphones and their cable in both pictures. If you want wireless earbuds or headphones instead, say so in the prompt.
On the demo, yes in both pictures: same face, same short beard, same haircut. In the shoes shot, the face is smaller and further back, so it shows less detail. If likeness matters most, go with the trunk version.
The template only makes the two photos. You can plug a Video node into the shoes picture yourself and describe the camera moving up to the face. We did not test it, and the video costs extra credits.
38 credits, 19 per render on Nano Banana Pro at 2K. If one picture does not work for you, rerun just that render for 19 credits.
Yes, by switching the node to Nano Banana 2.1 at 1K, at 7 credits per render, for smaller pictures. We did not test it on this template: the demo runs on Nano Banana Pro.
1792 x 2400 pixels, portrait, in a 3:4 ratio. Enough for an Instagram story or post, or a small print.
We do not know who started it. videosi.io has listed it in its tracker since 3 November 2026 with the "Just starting" status, and media.io has an undated video generator page named after it. Imaginode has no link with these sites.
The photo is optional in the canvas, but without it the model invents a person. For it to be you on the trunk, you need your full-body photo.
Autumn lake daydream AI photo from your own full-body picture
Use this workflowFree account, no card required. The workflow opens pre-filled in your canvas.
Nano Banana Pro
Flux Kontext
Seedream 5 Pro