MachineDelusions's picture
Add model card
f45d3ee verified
|
Raw History Blame Contribute Delete
1.14 kB
---
license: mit
base_model: kandinskylab/Kandinsky-6.0-VSR-distilled2steps-5s-Diffusers
tags:
- lora
- video-super-resolution
- upscaling
- kandinsky
- comfyui
---
# FL Kadinsky Upscale LoRA
`k6_sr_v5_x2_crisp` is a rank-32 LoRA for the distilled 2-step
[Kandinsky 6 VSR](https://huggingface.co/kandinskylab/Kandinsky-6.0-VSR-distilled2steps-5s-Diffusers)
model. It gives crisper edges and more fine texture than the released model
at x2, at the cost of some faithfulness to the source.
![Before and after](before_after.png)
## Usage
Use it with the [FL Kadinsky Upscale](https://github.com/filliptm/ComfyUI-FL-Kadinsky-Upscale)
ComfyUI node pack. Put the file in `ComfyUI/models/loras/FL_Kadinsky/`:
```bash
hf download MachineDelusions/Kandinsky6-VSR-LoRas k6_sr_v5_x2_crisp.safetensors --local-dir ComfyUI/models/loras/FL_Kadinsky
```
| Setting | Value |
|---|---|
| Scale | `2x` |
| LoRA strength | `1.0` (`0.7` is more natural on faces) |
| `lq_noise_scale` | `0.3` |
## Training
Trained at x2 only, on unsharp-masked 4K targets with L1, LPIPS, edge, texture
and a light adversarial loss.
## License
MIT, like the base model.