Question 1

What is AI Depth to Image?

Accepted Answer

Upload a reference image. The AI computes a depth map (foreground vs. background, what is closer vs. farther from the camera) and uses that 3D layout as a constraint while rendering a brand-new image in any style or content you describe.

Question 2

When should I use depth vs. canny vs. pose?

Accepted Answer

Depth preserves SCENE GEOMETRY (the room, the camera angle, the relative distances). Canny preserves OUTLINE. Pose preserves BODY POSITION. Use depth when the spatial composition matters — e.g., restyling a product shot keeps the product in the same place even if you swap the background.

Question 3

How is the depth map extracted?

Accepted Answer

MiDaS (Intel ISL) — a monocular depth estimator. It looks at a single 2D image and predicts per-pixel depth, no actual 3D camera or LiDAR needed. The depth map becomes the SDXL Depth ControlNet input.

Question 4

What kind of reference images work best?

Accepted Answer

Anything with clear foreground/background separation. Indoor scenes, product shots, outdoor landscapes, room interiors all work. Flat compositions (e.g., a graphic poster) yield uninteresting depth maps; depth control is most useful when the source has 3D structure.

Question 5

Is it free?

Accepted Answer

Yes. ~1,200 tokens per render (1,000 base + 20% ControlNet surcharge). Signed-in users get 5K free daily — about 4 depth-controlled renders per day at the free tier.

Question 6

Can I use this to relight a scene?

Accepted Answer

Indirectly — the depth map keeps the geometry, the prompt controls the lighting ("at sunset", "under harsh studio lights", "by candlelight"). Output keeps the spatial layout, swaps the lighting cues. Great for "same room, different time of day" effects.

Question 7

How does it differ from img2img?

Accepted Answer

img2img re-paints over the input directly — colors, edges, AND geometry. Depth-to-image throws away the colors and edges, keeps just the geometry. Same composition, totally fresh content. img2img tends to be subtle; depth lets you radically swap the subject.

Question 8

Can I tune how strictly depth is followed?

Accepted Answer

Yes — ControlNet strength slider. Default 0.7. 1.0 = strict adherence (output looks like a depth-mapped re-render); 0.4 = loose (more creative variation). Tune per scene.

Question 9

What output sizes are supported?

Accepted Answer

512×512 default. Up to 1024×1024 on standard SDXL aspect ratios. Larger sizes use more VRAM + tokens.

Question 10

Is the depth map output viewable?

Accepted Answer

Today only the final rendered image is returned. The depth map is computed on the GPU + discarded. If you want to expose the raw depth output as a separate download we can wire that — file an idea via /contact/.

Question 11

Are the uploaded references stored?

Accepted Answer

Processed immediately, depth-extracted, then discarded. Only your prompt + final render survive on /account/?tab=history. Never used for training. /privacy/ for the full policy.

Question 12

Is there an API?

Accepted Answer

Yes — POST multipart to /v1/image/generate/ with model=sdxl, prompt, control_image (file), control_type=depth. Bearer auth, 10K free tokens/month. Curl at /api/.

Canny → Bild (ControlNet)

Ergebnis

Canny → Bild (ControlNet)

Ergebnis

Erhalten Sie 10.000 kostenlose Token

Warten Sie — Holen Sie sich 10K kostenlose Token!

Willst du mehr?