Both images in story order
The alley first, the forest second: the eyes changing and the scratched hand, then the fur and claws under the moon. In that order the carousel tells the transformation without needing a caption.
Turn yourself into a werewolf with your photo and AI
Your photo as a werewolf: halfway through the change in a forest under the full moon, then the first signs in a village alley. No gore, the workflow is visible here.
Real workflow: a portrait of a clean-shaven man with short brown hair, in a navy sweater against a light grey wall, then the same man halfway through the change in a pine forest under a huge moon, amber eyes, fangs, fur along his jaw and clawed hands, and in a half-timbered village alley, looking up at the moon, with fur sideburns and three scratches on his hand. He's easy to recognise in the alley, less so in the forest, where his face came out harder and older.
At a glance
- You provide
- 1 photo · a text or a brief
- What the workflow produces
- 2 images in 3:4
- Canvas structure
- 6 nodes wired by 4 connections
- Models wired in
- Nano Banana Pro
- Cost of one full run
- about 38 credits, roughly $0.46
- Account
- The demo is visible without an account; generating requires a free account, trial credits included
Turning yourself into a werewolf from a photo is going around TikTok right now, just before Halloween. Here, one photo goes in and two images come out. In the alley of an old village, the change has barely started: amber eyes, fangs, fur sideburns, three scratches on the back of a hand. In the pine forest it's halfway done, with fur on the jaw and neck, pointed ears and long claws, under an enormous moon.
No blood, no wounds: the prompt rules them out, and it describes the face feature by feature so you still recognise yourself under the fur. In the demo that works well in the alley. In the forest, the model hardened the face, furrowed the brow and darkened the hair, so the man looks older than in his photo. And in the alley the scratches came out red, a bit of blood nobody asked for.
For a full costume without the transformation, see the Halloween costume. For heavier scars or prosthetics there's the special effects makeup, and the zombie hug goes for something softer. If you'd rather be someone else entirely, the witch on a flying broom and the knight also start from your photo. Both renders cost thirty-eight credits.
Actual renders from the demo
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
Who it is for
People who want to do the werewolf trend with their own photo, friends preparing a post for Halloween or TikTok, content creators looking for a starting image to animate.
Which files to provide
A sharp, well-lit front-facing photo of you or of someone who agreed, and the scene described with how far the change has gone, the setting and the moonlight.
How it works
- 1
Pick a front-facing photo
Sharp, well lit, face clear, no sunglasses or cap. A selfie is enough. Your photo, or one of someone who said yes.
- 2
Keep the face sentences
The end of each prompt describes the face feature by feature and tells the model not to change your age. That's what keeps you recognisable under the fur. Change the setting if you like, but leave those sentences alone.
- 3
Match the prompt to your photo
It describes a clean-shaven man with short hair in a navy sweater. If you're a woman, have a beard or long hair, change those words, or the model mixes up what it sees in the photo with what it reads.
- 4
Compare with the photo
Put each render next to the original portrait. If the face drifted, like in the demo's forest shot, rerun that node on its own: nineteen more credits.
Variations and use cases
The same canvas, tuned for different needs: each variation is two or three lines of prompt away.
A woman as the werewolf
Replace "the man from the photo" with "the woman from the photo" and "him/his" with "her", drop "clean-shaven" and describe her hair, long, tied back or loose. The rest of both prompts works as is.
With a beard or glasses
If you have a beard, put it in the list of features instead of "clean-shaven", or the model may blend it into the fur. Prescription glasses can stay, as long as you say so in the prompt.
Another setting
Keep the fur, the amber eyes and the face sentences, and change only the place: an empty car park under a streetlight, a wheat field, a rooftop. Leave the full moon in the sky, it's what makes the scene read.
A third stage, almost wolf
Add an Image node where the change is nearly complete, the snout stretching out and fur over the whole face. The more fur you add, the less people will recognise you, so keep at least the eyes and the face shape.
The content creator
They recreate the effect on their own photo, then connect a Video node to the forest image to make the fur grow or the head tilt up towards the moon. This page has no video demo, so the still image stays the starting point.
Common mistakes
Using a famous person's photo
An actor, a singer, an athlete: no. This workflow is for turning yourself into the werewolf, or someone who agreed and will see the picture.
Cutting the face sentences to save space
Without them, the model draws a generic werewolf. Even with them, the demo's forest shot came out with a harder, older face. Those sentences are the bare minimum, not a guarantee.
Pushing the change too far
A snout, fur everywhere, huge fangs: by then nobody can tell it's you. The trend works because you're still recognisable. Keep at least the eyes, the nose and the face shape.
Counting on "no blood" for a clean image
The alley prompt rules it out, and the scratches still came out red. If you want marks without any redness, write "pale, healed scratches", or take them out.
Recommended models
Nano Banana Pro
Seedream 5 Pro
Flux KontextFrequently asked questions
Will I recognise myself as a werewolf?
In the alley, yes, no question. In the forest, less so: the face is harder, the brow furrowed, the hair darker, and he looks older than in the photo. That's the one to rerun if the likeness matters to you.
Is it gory?
No. No blood or wounds in the forest. In the alley, the three scratches the prompt asks for on his hand came out red, like fresh scrapes. That's the only slip on this front, and it's a small one.
Why are the two images so different?
They show two points in the night: the very first signs, which you only notice up close, then the change halfway done, with fur, ears and claws. So the alley comes before the forest.
How much do the two images cost?
Thirty-eight credits, nineteen per render on Nano Banana Pro in 2K. Rerunning a single image costs nineteen more.
Why Nano Banana Pro and not a cheaper model?
Because it holds a face from a single photo, even under fur. Flux Kontext, which costs less, retouches the features, and the effect falls flat if you don't recognise yourself as the werewolf.
What size is the image?
1792 x 2400 pixels, vertical 3:4. Both renders in the demo came out on the first try, neither was redone.
Does it work with a photo of a woman?
Yes, once you change "the man" to "the woman", "him/his" to "her" and the hair description in both prompts. The demo only shows a man, so check the likeness on the first render before running the second.
Can I turn it into a transformation video?
Connect a Video node to the image you keep and describe the motion, fur spreading or the head lifting towards the moon. This page has no video demo, so there is no promise on the result.
Turn yourself into a werewolf with your photo and AI
Use this workflowFree account, no card required. The workflow opens pre-filled in your canvas.