

A mossy hooded cloak, a glowing lantern and a misty autumn forest for a classic witch look.
Edit the uploaded photo into a forest witch Halloween portrait. Keep the person's face recognizable: same facial features, face shape, skin tone, approximate age and natural proportions. Dress the person in a weathered dark-green hooded cloak layered with moss, dried leaves and leather straps, with a small herb pouch at the waist. The person holds a warm glowing lantern close to the body. Place the person in a misty autumn forest with moss-covered trunks, hanging fog and fallen leaves. Photorealistic editorial portrait, warm lantern key light against cool green ambient light, realistic fabric and moss texture, natural skin detail. Keep the same number of people as the uploaded photo. Do not change the person's identity. No extra limbs, distorted hands, text, logos or watermarks.
How this prompt is composed — each chip is one phrase. Mix, swap, or remove chips to make the look your own.
One click to remix this prompt with a different look or aspect ratio.
More templates in the same style
All templates on this page are designed for and tested with GPT-Image-2. You can copy the prompt and run it elsewhere, but quality and text rendering may vary on other models.
Clicking Remix opens our generator with the prompt, aspect ratio, and resolution prefilled. You can edit any part of the prompt, swap the size, or rerun the generation as many times as you like.
Every run is a fresh generation — variations in composition, lighting, and detail are expected. To stay closer to the preview, keep the prompt verbatim, lock the same aspect ratio, and run a few seeds.
Absolutely — that's the point. Use the Prompt structure card below to see how the prompt is composed, then add, remove, or swap phrases to dial in your own look.