ControlNet (SDv2)
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
- Stability AI
- Organisation type
- Industry
- Country
- United Kingdom of Great Britain and Northern Ireland
- Published
- 26 November 2023
- Authors
- Lvmin Zhang, Anyi Rao, Maneesh Agrawala
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Image generation
- Task
- Image-to-image
- Base model
- Stable Diffusion 2.1
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.
- Training data
- tokens
200k training samples
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.
- How it was established
- Hardware
- Fine-tuning compute
- 2.1 × 10¹⁹ FLOP
160000000000000 FLOP/GPU/sec [3090Ti reported, bf16 assumed] * 120 hours * 3600 sec / hour * 1 GPU * 0.3 [assumed utilization] = 20736000000000000000 FLOP
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 GeForce RTX 3090 Ti
- Chips used
- 1
- Wall-clock time
- 120 hours
- Power draw
- 490 W
"one single NVIDIA RTX 3090Ti, and 5 days of training"
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.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Adding Conditional Control to Text-to-Image Diffusion Models
- Last updated
- 11 February 2026
What the numbers mean
Where it came from
ControlNet (SDv2) was published by Stability AI, in United Kingdom of Great Britain and Northern Ireland, in November 2023. The organisation is categorised as industry.
It works in Image generation, and is recorded as doing image-to-image.
Its starting point was Stable Diffusion 2.1 — most models at this scale are adapted from an existing base rather than built from nothing.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Answers
ControlNet (SDv2) — common questions
How many parameters does ControlNet (SDv2) have?
No parameter count has been published for ControlNet (SDv2), which is why no memory or speed figure appears on this page.
Who created ControlNet (SDv2)?
ControlNet (SDv2) was published by Stability AI, based in United Kingdom of Great Britain and Northern Ireland, categorised as industry.
When was ControlNet (SDv2) released?
ControlNet (SDv2) was published in November 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.
What is ControlNet (SDv2) used for?
ControlNet (SDv2) works in Image generation, and is recorded as handling image-to-image. 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.
What GPU do I need to run ControlNet (SDv2)?
None. ControlNet (SDv2) 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 ControlNet (SDv2) open source?
No. ControlNet (SDv2) has not had its weights 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.