looptrans-looped_5x4_sm is an open-weight model from Quan Dao. Its published files total 23.1 GB.
Parameters—
Context—
Weights23.1 GB
License—
AccessOpen weights
Monthly Downloads—
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- quandao10/looptrans-looped_5x4_sm
- Publisher
- Quan Dao
- Task
- Not stated by the source
- Modality
- Other
- Library
- diffusers
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 60b965f1958f715c3fb1ea06589a74607e636d47
- First published
- 2026-10-13
- Last updated
- 2026-10-14
Files and Weights
13 files, 23.1 GB in total. The weights are 6 files totalling 23.1 GB in pt, safetensors.
Weights6 files · 23.1 GB
Configuration4 files · 2.7 KB
Other2 files · 4 B
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| step0005400/ema/diffusion_pytorch_model.safetensors | Weights | 2.9 GB | c8c4c3164f2d |
| step0005400/state.pt | Weights | 5.8 GB | 439bbd65511a |
| step0005400/student/diffusion_pytorch_model.safetensors | Weights | 2.9 GB | c502accfb53e |
| step0005600/ema/diffusion_pytorch_model.safetensors | Weights | 2.9 GB | 5e891a4daf49 |
| step0005600/state.pt | Weights | 5.8 GB | b66e5c957d31 |
| step0005600/student/diffusion_pytorch_model.safetensors | Weights | 2.9 GB | 1d169be970ba |
| step0005400/ema/config.json | Configuration | 672 B | — |
| step0005400/student/config.json | Configuration | 676 B | — |
| step0005600/ema/config.json | Configuration | 672 B | — |
| step0005600/student/config.json | Configuration | 676 B | — |
| step0005400/COMPLETE | Other | 2 B | — |
| step0005600/COMPLETE | Other | 2 B | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 23.1 GB
Download from Quan Dao
Released by Quan Dao through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 23.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.