Model reference · open weights
swin2SR-classical-sr-x2-64 is an open-weight image model from caidas, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Swin2SR model (image super-resolution) Swin2SR model that upscales images x2. It was introduced in the paper Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration by Conde et al. and first released in this repository. Intended use cases This model is intended for image super resolution. Usage Refer to the documentation.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | caidas |
|---|---|
| Type | Image models |
| Parameters (lead) | 12M |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-12-16 |
| Popularity | 30k downloads / month |
| Likes | 48 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| swin2SR-classical-sr-x2-64 | 12M | BF16 | ~0 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys swin2sr-classical-sr-x2-64 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (swin2sr-classical-sr-x2-64 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/images/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"swin2sr-classical-sr-x2-64","prompt":"a red bicycle","size":"1024x1024"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗