AI models
Stable Diffusion (LDM-KL-8-G)
Training compute
5×10²² FLOP
Parameters
1.4B
Published
Apr 13, 2022
Stable Diffusion (LDM-KL-8-G) is an AI model developed by Runway, Ludwig Maximilian University of Munich and Heidelberg University (United States and Germany), first published in April 2022. It works in the image generation domain, on tasks such as image generation and text-to-image.
Training it took an estimated 5×10²² FLOP of compute (estimation method: hardware). The model has 1,450,000,000 parameters. Training ran on 256 NVIDIA A100 for about 586 hours. The compute alone is estimated at $111K in 2023 dollars.
Access: Open weights (unrestricted). Its weights are openly available. It is built on top of Stable Diffusion 1.2. The reference paper has 24,523 citations. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- Runway, Ludwig Maximilian University of Munich, Heidelberg University
- Country of organization
- United States, Germany
- Domain
- Image generation
- Task
- Image generation, Text-to-image
- Training compute
- 5×10²² FLOP
- Compute estimation method
- Hardware
- Parameters
- 1,450,000,000
- Training hardware
- NVIDIA A100
- Chips used
- 256
- Training time
- 586 h
- Chip-hours
- 150K
- Training power draw
- 205.8 kW
- Training cost (2023 USD)
- $111K
- Model accessibility
- Open weights (unrestricted)
- Open weights
- Yes
- Base model
- Stable Diffusion 1.2
- Citations
- 24,523
- Epoch confidence
- Confident
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models