Will it change the people or the subject in my photo?

Not in the top half. The prompt forbids redrawing it or changing the subject, the number of subjects, the action, the viewpoint, the colour or the light, and specifically forbids cropping away a subject, the top of a building, or an animal's head or limbs. The lower half is a rebuild in wool, where the scene is deliberately reduced to one core subject plus two to four supporting pieces.

Can I choose the title?

Yes, and it is the more reliable path. Type your own title and subtitle and the model sets them exactly as written. Leave them blank and it writes its own two-to-five-word English title from the scene, which is a coin toss on wording.

What shape of photo should I upload?

Landscape, close to 4:3. The top band is half of a 2:3 frame, which works out as a 4:3 landscape region, so a photo already near that shape is kept whole. A portrait photo still works — the prompt crops it moderately and extends the surroundings — but you lose more of the edges.

How big is the felt scene meant to be?

That is the intent, though it is the part the model follows least. The prompt caps the scene at 52-60% of the lower half's width, never past 62%, height under 58%, with the base fully inside the frame. Measured against our own test runs it overshoots that target every time, so expect the miniature to fill more of the band than the samples suggest. The empty ivory felt is still doing real work — it is what makes the result read as a souvenir object rather than a filter.

Where do the colours come from?

From your photo. The prompt keeps the original's bright-but-not-garish colours and works them into wool, on a warm near-white ivory felt ground. It explicitly warns against the background going yellow, which is the usual failure mode for anything described as 'felt' or 'handmade'.

2K comes back at 1696 × 2528 pixels at this effect's 2:3 shape, which prints cleanly at poster size. 4K doubles that and costs 200 credits instead of 100.

Can I use my own prompt instead?

Not in this tool — it runs one fixed prompt. The full text is published on this page, so you can copy it and run your own variations anywhere that accepts image prompts.

What happens to my photo?

It is stored privately so the generator can read it, and deleted on a schedule. It is never made public, never shown to other users, and never used to train a model.

Needle Felt Travel Poster

Your photo on top, the same place needle-felted into a miniature below

Upload a landscape photo and get back a 2:3 poster: your photograph across the top, the same place rebuilt underneath as a hand-felted wool miniature on ivory felt — fluffy fibre, raw edges, real thickness and a soft shadow.

Try it with your photo See more examples

100 credits per image · about a minute · New accounts get 500 credits — 5 free images.

A cat drinking from a temple basin — the moss on the stone survives as flecked green fibre

Milan cathedral at night — the crowd becomes a row of grey felt dots, the flare smoke a carded pink cloud

A sheep pasture under cloud — stitched seams stand in for the hedge lines between fields

Gulls over open water — the whole sea reduced to one ragged disc of teal wool

A folk-craft shop window — the glass shelving becomes a small felted stand

Sunset through beach trees — the sun is a single ball of wool behind a stitched hammock

Try it with your own photo

Upload a photo

Title (optional)

Subtitle (optional)

Resolution

New accounts get 500 credits — 5 free images.

Examples

Every image below was made with the prompt on this page.

What is a needle felt travel poster?

A needle felt travel poster splits a 2:3 frame into two halves of exactly equal height. The top half is your photograph, fitted to a 4:3 landscape region and preserved in subject, viewpoint, colour and light. The bottom half sits on warm near-white ivory felt and rebuilds the same place as a hand needle-felted low-relief miniature: wool felt, felting fibre, raw edges, stitching and layered pieces, with visible fluffy fibre, irregular handmade edges, real thickness and a soft cast shadow. The scene is reduced to one core subject plus two to four supporting pieces. The prompt asks for it to stay small — 52 to 60% of the lower half's width — with plain felt all around; in practice it usually comes back larger than that, filling more of the band.

Works well with

Travel scenes with one clear subject: a shrine basin, a cathedral facade, a pasture, a shopfront, a single animal, a tree line at sunset. Landscape photos near 4:3 are kept whole. It handles animals unusually well — wool is a good material for fur.

Struggles with

Portraits and close-ups of faces — felting flattens features and the result reads as a doll. It is also weak on scenes whose interest is density or repetition, since the prompt strips the composition back to one subject plus a few supporting pieces. Very dark or very low-contrast photos tend to muddy once translated into wool.

The prompt behind this tool

This is the full prompt, translated into English. Copy it and use it with any image model that accepts a reference photo.

Use this prompt

Turn the photograph I upload into a single standalone 2:3 vertical needle-felt travel poster. No grids, no compilations, no nine-up layouts.

Overall layout
The canvas is a vertical 2:3. The top and bottom halves take strictly 50% each, and the dividing line must sit exactly at the centre of the frame.

Top half — the original photograph
Preserve the real photographic quality of the uploaded image completely. Do not redraw it, and do not change the subject, the number of subjects, the action, the viewpoint, the colour or the light. Fit the photograph into a horizontal 4:3 region: a landscape photo should be kept whole wherever possible, while a portrait photo may be cropped moderately, with the sky, ground, walls or quiet surroundings extended naturally. Never stretch or distort, and never crop away the subject, the top of a building, an animal's head or limbs, or any other key element. Keep the original sharpness — no blurring, no compression.

Bottom half — the needle-felt miniature
On a natural felt background of warm, near-white ivory, distil the most recognisable subject, contours, posture and spatial relationships from the photograph and rebuild them as a hand-made needle-felted low-relief miniature scene. Use wool felt, felting fibre, raw edges, stitching and layered felt pieces, showing pronounced fluffy fibre, irregular handmade edges, three-dimensional thickness and soft cast shadows. Do not make it a photorealistic image, a plastic model, clay, knitting or yarn weaving.

Simplify the secondary background and any repeated elements, keeping just one core subject plus two to four supporting elements. The felt scene's width stays between 52% and 60% of the lower half, and must never exceed 62%; its height must not exceed 58%. The scene sits entirely inside the frame — the base must not touch an edge or be cropped — with generous breathing room all around.

Text
Generate a short title of two to five English words from the content of the photograph, plus one restrained, natural English subtitle. Balance the type against the model without covering the scene.

The overall effect is warm, refined and quiet, like a handmade travel souvenir crossed with a high-end editorial poster. Keep the bright but never garish colours of the original photograph. Avoid a crowded frame, an oversized model, a yellowed background, piled-up detail and anything that feels like a children's toy.

Frequently asked questions

Will it change the people or the subject in my photo?: Not in the top half. The prompt forbids redrawing it or changing the subject, the number of subjects, the action, the viewpoint, the colour or the light, and specifically forbids cropping away a subject, the top of a building, or an animal's head or limbs. The lower half is a rebuild in wool, where the scene is deliberately reduced to one core subject plus two to four supporting pieces.
Can I choose the title?: Yes, and it is the more reliable path. Type your own title and subtitle and the model sets them exactly as written. Leave them blank and it writes its own two-to-five-word English title from the scene, which is a coin toss on wording.
What shape of photo should I upload?: Landscape, close to 4:3. The top band is half of a 2:3 frame, which works out as a 4:3 landscape region, so a photo already near that shape is kept whole. A portrait photo still works — the prompt crops it moderately and extends the surroundings — but you lose more of the edges.
How big is the felt scene meant to be?: That is the intent, though it is the part the model follows least. The prompt caps the scene at 52-60% of the lower half's width, never past 62%, height under 58%, with the base fully inside the frame. Measured against our own test runs it overshoots that target every time, so expect the miniature to fill more of the band than the samples suggest. The empty ivory felt is still doing real work — it is what makes the result read as a souvenir object rather than a filter.
Where do the colours come from?: From your photo. The prompt keeps the original's bright-but-not-garish colours and works them into wool, on a warm near-white ivory felt ground. It explicitly warns against the background going yellow, which is the usual failure mode for anything described as 'felt' or 'handmade'.
What size do I get?: 2K comes back at 1696 × 2528 pixels at this effect's 2:3 shape, which prints cleanly at poster size. 4K doubles that and costs 200 credits instead of 100.
Can I use my own prompt instead?: Not in this tool — it runs one fixed prompt. The full text is published on this page, so you can copy it and run your own variations anywhere that accepts image prompts.
What happens to my photo?: It is stored privately so the generator can read it, and deleted on a schedule. It is never made public, never shown to other users, and never used to train a model.