DiT-XL/2 + CADS
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- ETH Zurich,Disney Research
- Organisation type
- Academia,Industry
- Country
- Switzerland, United States of America
- Published
- 26 October 2023
- Authors
- Seyedmorteza Sadat, Jakob Buhmann, Derek Bradley, Otmar Hilliges, Romann M. Weber
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Image generation
- Task
- Image generation
- Base model
- DiT-XL/2
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 675M
- Training data
- tokens
original parameter count for DiT-XL/2
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Likely
"Further, using an existing pretrained diffusion model, CADS achieves a new state-of-the-art FID of 1.70 and 2.31 for class-conditional ImageNet generation at 256×256 and 512×512 respectively"
Sources
Where this record came from and when it was last checked.
- Reference
- CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling
- Last updated
- 28 November 2025
What the numbers mean
Background
DiT-XL/2 + CADS was published by ETH Zurich,Disney Research, in the country recorded as Switzerland, during October 2023. The category the publisher falls under is academia,Industry.
It works in the domain of Image generation, and is recorded as performing the task of image generation.
Its starting point was an existing base model, DiT-XL/2. Most models at this scale are adapted from an existing base rather than built from nothing.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Training and provenance
Its inclusion criterion: sOTA improvement.
Answers
DiT-XL/2 + CADS — common questions
DiT-XL/2 + CADS— how many parameters does it have?
It has a parameter count of 675M. original parameter count for DiT-XL/2. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
DiT-XL/2 + CADS— who created it?
It was published by ETH Zurich,Disney Research, based in Switzerland, an organisation categorised as academia,Industry.
DiT-XL/2 + CADS— when was it released?
It was published in October 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
DiT-XL/2 + CADS— what is it used for?
It works in the domain of Image generation, and is recorded as handling the task of image generation. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
DiT-XL/2 + CADS— what GPU do I need to run it?
None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
DiT-XL/2 + CADS— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.