mirror of
https://github.com/vladmandic/automatic
synced 2026-08-25 22:20:46 +02:00
Page:
Models
Pages
AMD MIOpen
AMD ROCm
API
Advanced Install
Benchmark
CHANGELOG
CLI Arguments
CLI Tools
CLiP Skip
Caption
Control HowTo
Control Settings
Control Technical
Debug
Detailer
Dev AICoding
Dev Docs
Dev Extensions
Dev GettingStarted
Dev Hints
Dev Home
Dev Locale
Dev SelfStart
Dev Structure
Dev Theme
Dev UI
DirectML
Docker
Enso
FAQ
FLUX
Features
FramePack
Gated
Getting Started
Google GenAI
HiDream
Home
Hotkeys
HuggingFace
IPAdapter
Ideogram
Installation
Intel ARC
Kanvas
LTX
Launcher
LoRA Technical
LoRA
Loader
MacOS Python
Malloc
MiniMax
Model Loading
Model Support
Models Tab
Models
Networks Search
Networks
Notes
NudeNet
Nunchaku
ONNX Runtime
Offload
OpenVINO
Outpaint
Parameters
Performance Timers
Performance Tuning
Platforms
Process
Profiling
Prompt Enhance
Prompting
Python
Quantization
Reprocess
SD Pipeline How it Works
SD Training Methods
SD XL
SD3
SDNQ Quantization
Schedulers
Scripts
Stability Matrix
Stable Cascade
Styles
Themes
Troubleshooting
Update
Using LCM
VAE
Video
WSL
Wildcards
XYZ Grid
ZLUDA
_ToDo
index
nVidia
Clone
46
Models
Vladimir Mandic edited this page 2026-05-27 17:03:48 +02:00
Models
List of popular text-to-image generative models with key parameters and architecture overviews.
| Publisher | Model | Version | Size | Diffusion Architecture | Model Params | Text Encoder(s) | TE Params | Auto Encoder | License | Release date |
|---|---|---|---|---|---|---|---|---|---|---|
| StabilityAI | Stable Diffusion | 1.5 | 2.28GB | UNet | 0.86B | CLiP ViT-L | 0.12B | VAE | OpenRAIL | 2022 October |
| StabilityAI | Stable Diffusion | 2.1 | 2.58GB | UNet | 0.86B | CLiP ViT-H | 0.34B | VAE | OpenRAIL | 2022 December |
| StabilityAI | Stable Diffusion | XL | 6.94GB | UNet | 2.56B | CLiP ViT-L + ViT+G | 0.12B + 0.69B | SDXL | OpenRAIL | 2023 July |
| StabilityAI | Stable Diffusion | 3.0 Medium | 15.14GB | MMDiT | 2.0B | CLiP ViT-L + ViT+G + T5-XXL | 0.12B + 0.69B + 4.76B | 16ch VAE | Proprietary | 2024 June |
| StabilityAI | Stable Diffusion | 3.5 Medium | 15.89GB | MMDiT | 2.25B | CLiP ViT-L + ViT+G + T5-XXL | 0.12B + 0.69B + 4.76B | 16ch VAE | Proprietary | 2024 October |
| StabilityAI | Stable Diffusion | 3.5 Large | 26.98GB | MMDiT | 8.05B | CLiP ViT-L + ViT+G + T5-XXL | 0.12B + 0.69B + 4.76B | 16ch VAE | Proprietary | 2024 October |
| StabilityAI | Stable Cascade | Medium | 11.82GB | Multi-stage UNet | 1.56B + 3.6B | CLiP ViT-G | 0.69B | 42x VQE | Proprietary | 2024 February |
| StabilityAI | Stable Cascade | Lite | 4.97GB | Multi-stage UNet | 0.7B + 1.0B | CLiP ViT-G | 0.69B | 42x VQE | Proprietary | 2024 February |
| Black Forest Labs | Flux | 1 Schnell | 32.93GB | MMDiT | 11.9B | CLiP ViT-L + T5-XXL | 0.12B + 4.76B | Flux | Apache 2.0 | 2024 August |
| Black Forest Labs | Flux | 1 Dev | 32.93GB | MMDiT | 11.9B | CLiP ViT-L + T5-XXL | 0.12B + 4.76B | Flux | Proprietary | 2024 August |
| Black Forest Labs | Flux | 1 Kontext-Dev | 32.93GB | MMDiT | 11.9B | CLiP ViT-L + T5-XXL | 0.12B + 4.76B | Flux | Proprietary | 2025 June |
| Black Forest Labs | Flux | 1 Krea-Dev | 32.93GB | MMDiT | 11.9B | CLiP ViT-L + T5-XXL | 0.12B + 4.76B | Flux | Proprietary | 2025 July |
| Black Forest Labs | Flux | 2 Dev | 114GB | MMDiT | 32B | Mistral Small 3.2-2506 | 24B | Flux 2 | Proprietary | 2025 November |
| Black Forest Labs | Flux | 2 Klein 9B | 34.7GB | MMDiT | 9B | Qwen3-8B | 8B | Flux 2 | Proprietary | 2026 January |
| Black Forest Labs | Flux | 2 Klein Base 9B | 34.7GB | MMDiT | 9B | Qwen3-8B | 8B | Flux 2 | Proprietary | 2026 January |
| Black Forest Labs | Flux | 2 Klein 4B | 16GB | MMDiT | 4B | Qwen3-4B | 4B | Flux 2 | Apache 2.0 | 2026 January |
| Black Forest Labs | Flux | 2 Klein Base 4B | 16GB | MMDiT | 4B | Qwen3-4B | 4B | Flux 2 | Apache 2.0 | 2026 January |
| lodestones | Chroma | 48 | 26.84GB | MMDiT | 8.9B | T5-XXL | 4.76B | Flux | Apache 2.0 | 2025 July |
| lodestones | Chroma | 1 HD | 26.84GB | MMDiT | 8.9B | T5-XXL | 4.76B | Flux | Apache 2.0 | 2025 July |
| lodestones | Chroma | 1 Base | 26.84GB | MMDiT | 8.9B | T5-XXL | 4.76B | Flux | Apache 2.0 | 2025 July |
| lodestones | Chroma | 1 Flash | 26.84GB | MMDiT | 8.9B | T5-XXL | 4.76B | Flux | Apache 2.0 | 2025 July |
| lodestones | Zeta-Chroma | 20.5GB | S3-DiT | 6.5B | Qwen3-4B | 4B | None | Apache 2.0 | 2026 April | |
| Ostris | Flex | 1 Alpha | 25.65GB | MMDiT | 8.16B | CLiP ViT-L + T5-XXL | 0.12B + 2.95B | Flux | Apache 2.0 | 2025 January |
| Ostris | Flex | 2 Preview | 25.65GB | MMDiT | 8.16B | CLiP ViT-L + T5-XXL | 0.12B + 2.95B | Flux | Apache 2.0 | 2025 April |
| FreePik | F-Lite | 19.81GB | DiT | 9.8B | T5-XXL | 2.95B | Flux | OpenRAIL | 2025 May | |
| FreePik | F-Lite | Texture | 19.81GB | DiT | 9.8B | T5-XXL | 2.95B | Flux | OpenRAIL | 2025 May |
| FreePik | F-Lite | 7B | 13.89GB | DiT | 6.9B | T5-XXL | 2.95B | Flux | OpenRAIL | 2025 May |
| NVLabs | Sana | 1.5 1.6B | 9.49GB | DiT | 1.60B | Gemma2 | 2.61B | DC-AE | Proprietary | 2025 March |
| NVLabs | Sana | 1.5 4.8B | 15.58GB | DiT | 4.72B | Gemma2 | 2.61B | DC-AE | Proprietary | 2025 March |
| NVLabs | Sana | 1.0 1600M | 12.63GB | DiT | 1.60B | Gemma2 | 2.61B | DC-AE | Proprietary | 2024 November |
| NVLabs | Sana | 1.0 600M | 7.51GB | DiT | 0.59B | Gemma2 | 2.61B | DC-AE | Proprietary | 2024 November |
| nVidia | Cosmos-Predict2 T2I | 2B | 13.32GB | DiT | 1.96B | T5-XXL | 4.86 | Wan | Proprietary | 2025 June |
| nVidia | Cosmos-Predict2 T2I | 14B | 37.36GB | DiT | 14.26B | T5-XXL | 4.86 | Wan | Proprietary | 2025 June |
| FAL | AuraFlow | 0.2 | 31.90GB | MMDiT | 6.8B | UMT5 | 12.1B | SDXL | Apache 2.0 | 2024 July |
| FAL | AuraFlow | 0.3 | 31.90GB | MMDiT | 6.8B | UMT5 | 12.1B | SDXL | Apache 2.0 | 2024 August |
| AlphaVLLM | Lumina | Next SFT | 8.67GB | NextDiT | 1.7B | Gemma | 2.5B | SDXL | Apache 2.0 | 2024 June |
| AlphaVLLM | Lumina | 2 | 20.75GB | NextDiT | 2.61B | Gemma-2 | 2.61B | Flux | Apache 2.0 | 2025 January |
| AlphaVLLM | Lumina-DiMOO | 17.1GB | Diffusion MLLM | 8B | None | - | VQ | Apache 2.0 | 2025 September | |
| PixArt | Alpha | XL 2 | 21.3GB | DiT | 0.61B | T5-XXL | 4.76B | VAE | OpenRAIL | 2023 November |
| PixArt | Sigma | XL 2 | 21.3GB | DiT | 0.61B | T5-XXL | 4.76B | VAE | OpenRAIL | 2024 April |
| Segmind | SSD-1B | 8.72GB | UNet | 1.33B | CLiP ViT-L + ViT+G | 0.12B + 0.69B | SDXL | Apache 2.0 | 2023 October | |
| Segmind | Vega | 6.43GB | UNet | 0.75B | CLiP ViT-L + ViT+G | 0.12B + 0.69B | SDXL | Apache 2.0 | 2023 November | |
| Segmind | Tiny | 1.03GB | UNet | 0.32B | CLiP ViT-L | 0.12B | SDXL | OpenRAIL | 2023 July | |
| Thu-ML | UniDiffuser | v1 | 5.37GB | U-ViT | 0.95B | CLiP ViT-L + CLiP ViT-B | 0.12B + 0.16B | VAE | AGPL 3 | 2023 May |
| Kwai | Kolors | 17.40GB | UNnet | 2.58B | ChatGLM | 6.24B | VAE | Apache 2.0 | 2024 July | |
| PlaygroundAI | Playground | 1.0 | 4.95GB | UNet | 0.86B | CLiP ViT-L | 0.12B | VAE | ? | 2023 December |
| PlaygroundAI | Playground | 2.x | 13.35GB | UNet | 2.56B | CLiP ViT-L + ViT+G | 0.12B + 0.69B | VAE | Proprietary | 2023 December |
| Tencent | HunyuanDiT | 1.2 | 14.09GB | DiT | 1.5B | BERT + T5-XL | 3.52B + 1.67B | SDXL | Proprietary | 2024 May |
| Tencent | Hunyuan Image | 2.1 | 34.9GB | MMDiT | 17.4B | Qwen2.5-VL-7B + T5 | 8.29B + 0.22B | Hunyuan Image | Proprietary | 2025 August |
| Warp AI | Wuerstchen | 12.16GB | Multi-stage UNet | 1.0B + 1.05B | CLiP ViT-L + ViT+G | 0.12B + 0.69B | 42x VQE | MIT | 2023 August | |
| Kandinsky | Kandinsky | 2.1 | 5.15GB | Unet | 1.25B | CLiP ViT-G | 0.69B | SBER MOVQGAN | Apache 2.0 | 2023 April |
| Kandinsky | Kandinsky | 2.2 | 5.15GB | Unet | 1.25B | CLiP ViT-G | 0.69B | SBER MOVQGAN | Apache 2.0 | 2023 July |
| Kandinsky | Kandinsky | 3.0 | 27.72GB | Unet | 3.05B | T5-XXXL | 8.72B | SBER MOVQGAN | Apache 2.0 | 2023 November |
| Kandinsky | Kandinsky | 5.0 T2I Lite | 33.20GB | DiT | 6B | Qwen2.5-VL-7B + CLiP ViT-L | 8.29B + 0.12B | Flux | MIT | 2025 November |
| Kandinsky | Kandinsky | 5.0 I2I Lite | 33.20GB | DiT | 6B | Qwen2.5-VL-7B + CLiP ViT-L | 8.29B + 0.12B | Flux | MIT | 2025 November |
| Z.ai | CogView | 3 Plus | 24.96GB | DiT | 2.85B | T5-XXL | 4.76B | CogView | Apache 2.0 | 2024 October |
| Z.ai | CogView | 4 | 30.39GB | DiT | 6.37B | GLM-4 | 9.40B | CogView | Apache 2.0 | 2025 March |
| Z.ai | GLM Image | 35.8GB | Autoregressive transformer + DiT | 7B | GLM-4-9B-0414 | 9B | GLM Image | MIT | 2026 January | |
| IDKiro | SDXS | 2.05GB | UNet | 0.32B | CLiP ViT-L | 0.12B | VAE | OpenRAIL | 2024 March | |
| Open-MUSE | aMUSEd | 256 | 3.41GB | ViT | 0.60B | CLiP ViT-L | 0.12B | VQ | OpenRAIL | 2023 December |
| Koala | Koala | 700M | 6.58GB | UNet | 0.78B | CLiP ViT-L + ViT+G | 0.12B + 0.69B | VAE | Proprietary | 2024 January |
| Salesforce | BLIP-Diffusion | 7.23GB | UNet | 0.86B | CLiP ViT-L + BLiP-2 | 0.12B + 0.49B | VAE | BSD 3 | 2023 July | |
| DeepFloyd | IF | M | 12.79GB | Multi-stage UNet | 0.37B + 0.46B | T5-XXL | 4.76B | Pixel | Proprietary | 2023 April |
| DeepFloyd | IF | L | 15.48GB | Multi-stage UNet | 0.61B + 0.93B | T5-XXL | 4.76B | Pixel | Proprietary | 2023 April |
| MeissonFlow | Meissonic | 3.64GB | DiT | 1.18B | CLiP ViT-H | 0.35B | VQ | Apache 2.0 | 2024 October | |
| VectorSpaceLab | OmniGen | v1 | 15.47GB | Transformer | 3.76B | Phi-3 | 0 | VAE | MIT | 2024 October |
| VectorSpaceLab | OmniGen | v2 | 30.50GB | Transformer | 3.97B | Qwen-VL-2.5 | 3.75B | Flux | Apache 2.0 | 2025 June |
| HiDream-AI | HiDream | I1 Fast/Dev/Full | 42.71 GB + 15.69 | Sparse MMDiT | 17.10B | CLiP ViT-L + ViT+G + T5-XXL + LLama-3.1-8B | 0.12B + 0.69B + 2.95B + 4.54B | Flux | MIT | 2025 April |
| HiDream-AI | HiDream | O1-Image | 35.2 GB | UiT | 8.8B | None | - | None | MIT | 2026 May |
| Alibaba/Wan-AI | WAN | 2.1 1.3B | 27.72GB | DiT | 1.42xB | UMT5-XXL | 5.68B | Wan | Apache 2.0 | 2025 February |
| Alibaba/Wan-AI | WAN | 2.1 14B | 78.52GB | DiT | B | UMT5-XXL | 14.28B | Wan | Apache 2.0 | 2025 February |
| Bria | Bria | 3.2 | 18.66GB | MMDiT | 3.78B | T5-XXL | 4.76B | 16ch VAE | Proprietary | 2025 June |
| Alibaba/Qwen | Qwen-Image | 56.10GB | MMDiT | 20.43B | Qwen2.5-VL-7B | 8.29B | Qwen Image | Apache 2.0 | 2025 August | |
| Alibaba/Qwen | Qwen-Image | 2512 | 56.10GB | MMDiT | 20.43B | Qwen2.5-VL-7B | 8.29B | Qwen Image | Apache 2.0 | 2025 December |
| Alibaba/Qwen | Qwen-Image-Edit | 56.10GB | MMDiT | 20.43B | Qwen2.5-VL-7B | 8.29B | Qwen Image | Apache 2.0 | 2025 August | |
| Alibaba/Qwen | Qwen-Image-Edit | 2509 | 56.10GB | MMDiT | 20.43B | Qwen2.5-VL-7B | 8.29B | Qwen Image | Apache 2.0 | 2025 September |
| Alibaba/Qwen | Qwen-Image-Edit | 2511 | 56.10GB | MMDiT | 20.43B | Qwen2.5-VL-7B | 8.29B | Qwen Image | Apache 2.0 | 2025 December |
| Alibaba/Qwen | Qwen-Image-Layered | 56.10GB | MMDiT | 20.43B | Qwen2.5-VL-7B | 8.29B | Qwen Image Layered | Apache 2.0 | 2025 December | |
| Photoroom | PRX | 1024 T2I beta | 15.5GB | MMDiT | 1.3B | T5-Gemma-2B-2B-UL2 | 2B | Flux | Apache 2.0 | 2025 November |
| Alibaba/Tongyi-MAI | Z-Image | Turbo | 32.9GB | S3-DiT | 6.1B | Qwen3-4B | 4B | Flux | Apache 2.0 | 2025 November |
| Alibaba/Tongyi-MAI | Z-Image | 20.5GB | S3-DiT | 6.1B | Qwen3-4B | 4B | Flux | Apache 2.0 | 2026 January | |
| Meituan | Longcat Image | 29.3GB | MMDiT | 6B | Qwen2.5-VL-7B | 8.29B | Flux | Apache 2.0 | 2025 December | |
| Meituan | Longcat Image | Edit | 29.3GB | MMDiT | 6B | Qwen2.5-VL-7B | 8.29B | Flux | Apache 2.0 | 2025 December |
| AIDC-AI | Ovis Image 7B | 23.38GB | MMDiT | 7B | Ovis2.5 2B | 2.5B | Flux | Apache 2.0 | 2025 November | |
| Circlestone Labs | Anima | 14GB | DiT | 2B | Qwen3-0.6B | 0.6B | Qwen Image | Proprietary | 2026 January | |
| Baidu | ERNIE-Image | 31.6GB | DiT | 6B | Ministral 3 3B | 3B | Flux 2 | Apache 2.0 | 2026 April | |
| Nucleus AI | Nucleus Image | 51.7GB | Sparse MMDiT | 17B | Qwen3-VL-8B | 8B | Qwen Image | Apache 2.0 | 2026 March | |
| JoyAI | JoyAI Image Edit | 50.4GB | MMDiT | 16B | Qwen3-VL-8B (modified) | 8B | Wan | Apache 2.0 | 2026 March | |
| StepFun | Step-1X-Edit | v1p1 | 41.8GB | MMDiT | 11.9B | Qwen2.5-VL-7B | 8.29B | Flux | Apache 2.0 | 2025 September |
| iitolstykh | VIBE-Edit | 9.34GB | DiT | 1.60B | Qwen3-VL-2B | 2B | DC-AE | Proprietary | 2025 December | |
| Microsoft | Lens | 30.7GB | MMDiT | 3.8B | GPT-OSS 20B | 20B | Flux 2 | MIT | 2026 May |
Notes
- Created using the SD.Next built-in model analyzer.
- Parameter count is proportional to model complexity and capacity, but image quality also depends on training data and training duration.
- Size refers to the original model variant in 16-bit precision where available. Quantized variants may be smaller.
- Distilled variants are not included, because distillation typically does not change the underlying model parameter count (for example Turbo, LCM, Hyper, Lightning, Dev, Schnell).