Create a grounded forest-witch portrait with a moss cloak, crooked hat, fireflies, wet woodland fog, lantern light, and a TripoSplat photo workflow online.
A quiet, handcrafted witch look for people who prefer atmosphere over cartoon styling. The portrait keeps the person recognizable and lets the forest carry most of the mood.
Moss-green fabric, layered linen and leather, botanical charms, and a crooked brim hat replace the original clothing. Wet roots, fireflies, and lantern light add depth without overwhelming the face.
Copy the exact recipe or open the editor with it already filled in. The instructions separate identity, costume, scene, light, and failure cases so a retry changes one variable at a time.
Use the uploaded photo as the identity reference. Preserve the person's recognizable face, skin texture, facial proportions, age, pose, and natural anatomy. Create an original forest-witch Halloween portrait with a dark moss-green cloak, layered linen and leather, small botanical charms, and a wide crooked brim hat. Keep the styling grounded and handcrafted rather than cartoonish. Place the subject in an ancient foggy woodland just after rain, with wet roots, fireflies, and a single warm lantern. Use photorealistic editorial photography, soft cool ambient light, warm lantern fill, realistic skin and fabric. Keep the same number of people as the uploaded photo. Avoid altered identity, extra limbs, distorted hands, text, logos, and watermarks.
Use the provided portrait as the exact first frame. Create a five-second atmospheric Halloween forest-witch animation. Preserve identity, costume, hat, pose, background, and lighting. The subject looks slowly toward the lantern as fireflies move through the mist. Moist fabric and cloak edges shift in a quiet breeze, and the lantern light flickers gently. Use a minimal camera push-in, realistic physics, stable anatomy, and no cuts. Do not change the face or costume, add creatures, introduce text, or add watermarks.
Prompts stay in English because the image and video models follow English instructions most reliably. You can edit them after the editor opens.
Open the look that matches the subject you have: one person, a pet, a couple, or a scene.
Use a sharp, well-lit photo you have the right to edit. The prompt protects identity before it changes the styling.
Run GPT Image 2 in the image editor, then copy the same result into the video workspace for a short animation.
The public workspaces keep provider selection behind one generation contract. KIE image routes are live today; the same job can move through fal, Replicate, WaveSpeed, or SeeAPI when those routes are configured.
Low-cost image and image-to-video routes when this provider is configured.
Relay route for supported image and video models when configured.
Primary 3D and motion route; configured media jobs can use it as a fallback.
Queued image and video fallback for supported models when configured.
Active image route for GPT Image 2, Nano Banana 2, Seedream, Flux, and related models.
Provider availability and price follow the runtime configuration. The page never promises a route that the current deployment cannot execute.
Start with one look, then create a matching portrait, pet edit, or short video with the same visual language.
A dark fairytale portrait built from this season’s mascot-horror energy, without recreating a film character. One face stays recognizable while the costume, mane, horn, forest, and light become a complete editorial scene.
An editorial hair-and-wardrobe transformation for anyone who wants the braided-cosplay trend without a salon appointment. The face and pose stay familiar while the styling becomes a complete gothic fashion story.
A glowing fantasy portrait for people who want the cosmic-princess trend with original fashion direction. The model keeps the face and body believable while building a complete observatory scene.
Create a grounded forest-witch portrait with a moss cloak, crooked hat, fireflies, wet woodland fog, lantern light, and a TripoSplat photo workflow online.
No. The recipe uses a grounded folkloric mood with fog, fireflies, and a lantern. It does not ask for blood, injury, or a monstrous face.
A three-quarter or full-body photo with even light works well because the cloak and hat need room. Avoid heavy backlight that hides the face.
