WaveCut/ltx-2.3-upscale-ic-lora
0
LTX 2.3 Distilled Upscale IC-LoRA Space
Upload a short video and upscale/refine it using the Zlikwid/LTX_2.3_Upscale_IC_Lora In-Context LoRA applied to diffusers/LTX-2.3-Distilled-Diffusers.
How it works
- The input video is inspected before inference so oversized jobs fail early.
- The app samples an
8k+1frame count instead of decoding the whole upload blindly. - Frames are optionally center-cropped with Zoom.
- Frames are bicubic-upscaled to the target working resolution.
- The bicubic-upscaled video is passed both as an IC-LoRA reference condition and as an anchored video condition. The video condition keeps the generated latents tied to the source frames.
- The output is encoded at an FPS that preserves source duration when metadata is available.
- Source audio is muxed back into the output when Preserve Source Audio is enabled.
This follows the upstream LoRA instructions from Zlikwid/LTX_2.3_Upscale_IC_Lora:
- prompt is fixed to
upscale - LoRA weight is
ltx2.3_upscale_ic-lora_06250.safetensors - the reference video is bicubic-upscaled before the LTX-2.3 pass
- the LoRA metadata
reference_downscale_factor=2is preserved
The distilled LTX checkpoint requires:
num_inference_steps=8guidance_scale=1.0sigmas=DISTILLED_SIGMA_VALUES
Those values are fixed by the app instead of being exposed as free sliders.
Tested ZeroGPU Limits
- Input duration: up to 12 seconds
- Upload size: up to 200 MB
- Output frame pixels: up to about 1024x576 / 768x768
- Sampled frames: up to 65
- Queue concurrency: 1 GPU job at a time
Controls
- Processing Preset: Sets safe defaults for resolution, sampled frames, and LoRA strength.
- Output Resolution: Choose a target resolution. Use Source × Bicubic Factor to derive the output size from the cropped/source video and the bicubic factor.
- Bicubic Pre-Upscale Factor: Multiplier for Source × Bicubic Factor mode.
- Zoom: Center crop before upscaling.
- Refinement Strength (LoRA): Controls the IC-LoRA adapter weight.
- Input Preservation Strength: Anchors the output to the bicubic input. Raise it if the result drifts or corrupts the source; lower it if you want more generative detail.
- Sampled Frames (8k+1): Number of frames sent to LTX. The output FPS is derived from source duration.
- Preserve Source Audio: Reuses the input audio track in the final MP4.
This is a generative refinement LoRA, not a simple deterministic upscaler. The output may differ from the input depending on settings.
