AR-LDM
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
- Alibaba,University of Waterloo,Vector Institute
- Organisation type
- Industry,Academia,Academia
- Country
- China, Canada
- Published
- 20 November 2022
- Authors
- Xichen Pan, Pengda Qin, Yuhong Li, Hui Xue, Wenhu Chen
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Image generation
- Task
- Text-to-image
- Base model
- Stable Diffusion (LDM-KL-8-G)
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
- 1.5B
- Training data
- tokens
- Epochs
- 50
Table 1
PororoSV, FlintstonesSV and VIST. All storytelling datasets, sizes would be possible to look up.
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 5.1 × 10²⁰ FLOP
- How it was established
- Hardware
8 NVIDIA A100 GPUs for 8 days
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA A100
- Wall-clock time
- 194 hours (8.1 days)
- Compute cost
- $746
8 NVIDIA A100 GPUs for 8 days
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
- Open (non-commercial)
no weights, no license. training and inference code here: https://github.com/xichenpan/ARLDM
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
- Confident
- Citations
- 86
The first latent diffusion model for coherent visual story synthesizing. "Quantitative results show that AR-LDM achieves SoTA FID scores on PororoSV, FlintstonesSV, and the newly introduced challenging dataset VIST containing natural images"
Sources
Where this record came from and when it was last checked.
- Reference
- Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models
- Last updated
- 25 May 2026
What the numbers mean
Background
AR-LDM was published by Alibaba,University of Waterloo,Vector Institute, in China, in November 2022. industry,Academia,Academia is the category the publisher falls under.
It works in Image generation, and is recorded as doing text-to-image.
It is derived from Stable Diffusion (LDM-KL-8-G) rather than trained from scratch, which is the usual way a specialised model is produced.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
Producing it required around 5.1 × 10²⁰ FLOP of arithmetic, on NVIDIA A100, which is a statement about the training budget rather than about inference.
Its inclusion criterion is sOTA improvement.
Answers
AR-LDM — common questions
Who created AR-LDM?
AR-LDM was published by Alibaba,University of Waterloo,Vector Institute, based in China, categorised as industry,Academia,Academia.
When was AR-LDM released?
AR-LDM was published in November 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is AR-LDM used for?
AR-LDM works in Image generation, and is recorded as handling text-to-image. These are the areas it was designed around; they describe intent rather than a hard boundary.
How much compute was used to train AR-LDM?
Around 5.1 × 10²⁰ FLOP, on NVIDIA A100. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
What GPU do I need to run AR-LDM?
None. AR-LDM 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.
Is AR-LDM open source?
No. AR-LDM has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does AR-LDM have?
AR-LDM has 1.5B parameters. Table 1. 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.
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.