Marigold
marigoldETH Zurich Marigold. Diffusion-based monocular depth-estimation model fine-tuned from Stable Diffusion with strong fine-detail recovery.
- Price
- ≈ US$0.0936/run
- Input → output
- Text + Image → Text
- Developer
- Community
- Updated
- 23 September 2026
Playground
Try Marigold
No input form
No input form for this model yet
Its inputs are not documented yet. So that no run fails on a wrong input, we don't offer a form here. Pick a comparable model instead.
Examples
Open full size
InputNo text prompt: the model only takes the input shown.
Open full size
InputNo text prompt: the model only takes the input shown.
Open full size
InputNo text prompt: the model only takes the input shown.
About Marigold
Marigold is a model by Community in the Multimodal category. On Railwail, Marigold costs ≈ US$0.0936 per run.
Pricing
| Typical run (≈ 80 s on L40S) | US$0.0936 per run |
|---|---|
| GPU time (L40S) | US$0.00117 per GPU second |
- Billed by the GPU time the run actually takes. When the run starts, 3× the typical price is reserved from your balance and settled afterwards.
- 1 credit = US$0.01
Cost calculator
Price calculator
Typical according to the provider: about 80 s
Total
US$9.36
936 credits
Per run
US$0.0936 · 9.36 credits
Billed by the actual GPU time; this is an estimate.
API
No verified API example
The public API passes a different input format than this model needs. Use the playground above.
Specifications
- Model ID
marigold- Developer
- Community
- Category
- Multimodal
- Input
- Text, Image
- Output
- Text
- Billing
- By usage (tokens or GPU time)
- Catalog entry updated
- 23 September 2026
Tags
- replicate
- depth
- vision-understanding
- diffusion
- open-source
Frequently asked questions
What is Marigold?
Marigold is a model by Community in the Multimodal category.
How much does Marigold cost on Railwail?
On Railwail, Marigold costs ≈ US$0.0936 per run. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals US$0.01.
How fast is Marigold?
There are not enough measured runs of Marigold on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.
Is Marigold better than BLIP?
That depends on the task. Marigold (Community) and BLIP (Salesforce) are both models in the Multimodal category. The comparison page shows their prices and specifications side by side.
Compare Marigold and BLIPCan Marigold process images?
Yes. Marigold accepts images as input in addition to text.
Comparable models
All in this category- BLIPSalesforce
Salesforce BLIP. Vision-language model for image captioning and visual question answering. Given an image it writes a short natural-language caption, or answers a question about the image when one is supplied. A widely used baseline for automatic captioning.
- CLIP InterrogatorCommunity
pharmapsychotic's CLIP Interrogator. Takes an image and produces a Stable-Diffusion-style text prompt by combining BLIP captioning with CLIP to rank likely subjects, artists, mediums and styles. Commonly used to reverse-engineer a prompt from an existing picture.
- Depth Anything v2Community
Monocular depth-estimation model trained on 595k labeled and 62M unlabeled images. Strong zero-shot generalization in indoor and outdoor scenes.
All models through one API
One API key for every model on Railwail. Usage is charged from prepaid credits, 1 credit = US$0.01.