Add model card

README.md

@@ -1,5 +1,94 @@
----
-license: apache-2.0
-base_model:
-- Lightricks/LTX-2.3
----
+---
+license: apache-2.0
+base_model: Lightricks/LTX-Video
+tags:
+  - ltx-video
+  - ltx-2.3
+  - lora
+  - ic-lora
+  - sdr-to-hdr
+  - hdr
+  - color-grading
+  - video-to-video
+  - logc3
+pipeline_tag: video-to-video
+library_name: diffusers
+---
+
+# LTX-2.3 SDR → HDR IC-LoRA
+
+A LoRA adapter for **LTX-Video 2.3 (22B)** that converts SDR video into HDR (LogC3 encoded), trained as an **IC-LoRA** (in-context LoRA) using the `video_to_video` strategy from `ltxv-trainer`.
+
+The model takes an SDR clip as a conditioning reference and generates a matching HDR (LogC3) version, suitable for grading downstream in DaVinci Resolve, Baselight, or Nuke.
+
+Inspired by Lightricks' **LumiVid** paper ([arXiv:2604.11788](https://arxiv.org/abs/2604.11788)) — same core idea (LogC3 target, IC-LoRA-style reference conditioning, ~10K steps).
+
+## Checkpoint
+
+`lora_weights_step_07000.safetensors` — step 7,000 of a planned 10,000-step run.
+
+## Usage (ComfyUI)
+
+Use `LTXICLoRALoaderModelOnly` from [Lightricks/ComfyUI-LTXVideo](https://github.com/Lightricks/ComfyUI-LTXVideo):
+
+1. Load LTX-2.3 base model
+2. Load this LoRA via `LTXICLoRALoaderModelOnly`
+3. Connect your SDR clip as the **reference video**
+4. Run the IC-LoRA pipeline — Stage 1 (low-res, LoRA active) → Stage 2 (upsample, no LoRA)
+
+**No trigger word** — the LoRA is always active when loaded.
+
+**Recommended CFG:** up to **1.5** works well.
+
+## Training Details
+
+| | |
+|---|---|
+| Base model | LTX-Video 2.3 22B (`ltx-2.3-22b-dev`) |
+| Text encoder | Gemma 3 12B |
+| Strategy | IC-LoRA (`video_to_video` in [ltxv-trainer](https://github.com/Lightricks/LTX-Video-Trainer)) |
+| LoRA rank / alpha | 32 / 32 |
+| Target modules | `attn1/2.to_{k,q,v,out.0}`, `ff.net.0.proj`, `ff.net.2` |
+| Resolution | 1280 × 736 |
+| Frames per clip | 49 |
+| Batch size | 1 |
+| Learning rate | 2e-4, cosine schedule |
+| Steps | 7,000 (target 10,000) |
+| Precision | bf16 + gradient checkpointing |
+| Log curve | **LogC3** (validated optimal via KL divergence in LumiVid) |
+
+## Dataset
+
+- **200 clips** rendered from PolyHaven HDRIs with virtual camera moves
+- Paired SDR ↔ LogC3 HDR clips
+- SDR side intentionally degraded (compression, blur, contrast, white-balance shift) to mimic real-world camera capture
+
+## Intended Use
+
+- Converting SDR (Rec.709) video to LogC3 HDR for further grading
+- VFX / DI pipelines that already speak LogC3 (Nuke, Baselight, DaVinci Resolve)
+- Outputs are designed to be exported to ProRes 4444 or OpenEXR sequences
+
+## Limitations
+
+- Trained primarily on PolyHaven HDRI environments — limited human/motion diversity in v1
+- Output is **LogC3, not display-referred HDR** — you still need a grading pass to map to PQ/HLG/Rec.2100
+- The model can do a surprisingly good job of *hallucinating* believable detail back into clipped highlights (skies, practicals, blown-out windows), but this is generative reconstruction — it is not faithful recovery of the original photons. Use with eyes open in any pipeline where photographic accuracy matters.
+- Inference is two-stage (low-res → upsample); expect LTX-2.3's typical compute footprint
+
+## Citation
+
+If this is useful, please reference the LumiVid paper that inspired the approach:
+
+```
+@article{lumivid2026,
+  title={LumiVid: Distilling LDR Video Diffusion Models for HDR Video Generation},
+  author={Lightricks},
+  journal={arXiv:2604.11788},
+  year={2026}
+}
+```
+
+## License
+
+Apache 2.0. Base model license (LTX-Video) applies to inference use.