--- title: LTX-2.5-22b-IC-LoRA-Colorization canonical_url: "https://www.modelscope.cn/models/Lightricks/LTX-2.5-22b-IC-LoRA-Colorization" md_url: "https://www.modelscope.cn/models/Lightricks/LTX-2.5-22b-IC-LoRA-Colorization.md" repository: Lightricks/LTX-2.5-22b-IC-LoRA-Colorization last_updated: 2026-10-22 license: other base_model: - Lightricks/LTX-2.5 base_model_relation: adapter parameters: 453.0M tensor_type: - BF16 library_name: - safetensors - pytorch frameworks: - pytorch language: - en downloads: 58 stars: 0 tags: - ltx-video - ic-lora - ltx-2.5 - video-to-video - colorization - diffusion-single-file - ltx --- # LTX-2.5-22b-IC-LoRA-Colorization > LTX-2.5-22b-IC-LoRA-Colorization - Lightricks 在 ModelScope 开源的模型。LTX-2.5 22B IC-LoRA Colorization Lightricks/LTX-2.5-22b-IC-LoRA-Colorization 是 ModelScope 魔搭社区上的 453.0M 参数机器学习模型，采用 other 许可，基于 Lightricks/LTX-2.5 构建。 - **Repository**: Lightricks/LTX-2.5-22b-IC-LoRA-Colorization - **License**: other - **Parameters**: 453.0M - **Base model**: Lightricks/LTX-2.5 - **Tags**: ltx-video, ic-lora, ltx-2.5, video-to-video, colorization, diffusion-single-file, ltx - **Downloads**: 58 - **Stars**: 0 - **Last updated**: 2026-10-22 Source: https://www.modelscope.cn/models/Lightricks/LTX-2.5-22b-IC-LoRA-Colorization --- # LTX-2.5 22B IC-LoRA Colorization This is a **Colorization** IC-LoRA trained on top of **LTX-2.5-22B**, which restores natural color to grayscale, monochrome, or desaturated video while keeping subject identity, framing, and geometry untouched — only the color information changes. It is based on the [LTX-2.5](https://huggingface.co/Lightricks/LTX-2.5) foundation model. ## Model Files `ltx-2.5-22b-ic-lora-colorization-0.9.safetensors` — the single released checkpoint (used for the published inference samples). ## Model Details - **Base Model:** LTX-2.5-22B Video - **Training Type:** IC-LoRA (video-to-video) - **Control Type:** Video-to-video — a grayscale/monochrome input (reference) video drives a color-restored output video. - **Reference Downscale Factor:** 1 (the reference is encoded at 1× the output resolution). - **Pipeline details:** No special pre/post color transform — the reference video is VAE-encoded as the control signal and the model predicts the colorized result. ## Intended Use & Out-of-Scope **Intended use:** Colorizing black-and-white, monochrome, or heavily desaturated footage — restoring plausible, natural color to a clip while preserving the original subject, composition, motion, and background geometry. **Out of scope:** Any task other than colorization (it is not a deblur, denoise, decompression, or upscaling model); relighting or scene re-composition; and content far outside the training distribution. Generating far above the 960×544 training bucket can weaken the colorization effect. ## Control Signal Requirements - **Control signal type:** Grayscale / monochrome / desaturated source video. - **Expected input:** A reference video (`.mp4` / `.mov` / `.mkv` / `.webm` / `.avi`). - **Preprocessing:** None required — the reference is VAE-encoded directly. The reference is used at 1× the output resolution (downscale factor 1). - **Alignment:** The output matches the reference frame count, FPS, resolution, and aspect ratio. Best results at the 960×544×121 @ 24fps training bucket (both landscape 960×544 and portrait 544×960 were seen in training). ## How It Works The model is conditioned on **both** the reference video latents and a text prompt that describes the grayscale source and the desired color result. The prompt convention learned in training is: > Reference shows {grayscale scene description}. Edited shows the same scene with natural colors restored. COLORIZE {vivid natural-color description of the same scene}. Subject identity, framing, and background geometry are identical to the reference; only color information differs between reference and edited. Representative prompt from a real run: > Reference shows a small wild rabbit sitting among rough textured boulders with a fallen log and dry grass behind it, rendered in high-contrast monochrome with soft natural daylight emphasizing the fine fur and the coarse stone surfaces. Edited shows the same scene with natural colors restored. COLORIZE a young brown cottontail rabbit with warm tan and grey-brown fur, a pale cream underside and soft pink inner ears, perched on weathered grey granite boulders flecked with green and ochre lichen. Behind it a bleached driftwood log and clumps of golden dry grass catch the warm late-afternoon sun, while muted green vegetation softens the blurred background. The light is gentle and warm, giving the rocks subtle earthy browns and the whole scene a calm woodland tone. Subject identity, framing, and background geometry are identical to the reference; only color information differs between reference and edited. ## Usage ### 🔌 ComfyUI 1. Copy the LoRA weights into `models/loras`. 2. Load the **LTX-2.5-22B** base model and add `ltx-2.5-22b-ic-lora-colorization-0.9.safetensors` as the LoRA. 3. Start at strength `1.0` and adjust to taste. 4. Use an [IC-LoRA (video-to-video) workflow](https://github.com/Lightricks/ComfyUI-LTXVideo/blob/master/example_workflows/2.5/LTX-2.5_V2V_ICLoRA_Single_Stage_Distilled.json) from the [LTX-2 ComfyUI repository](https://github.com/Lightricks/ComfyUI-LTXVideo/), which already wires the reference-video control nodes. Connect your grayscale clip as the reference video and write the prompt using the `COLORIZE` convention above. Because the reference downscale factor is 1, a generic reference encode at output resolution is correct. 5. Start at or near the **960×544** training bucket; generating far above it can weaken colorization on high-frequency detail. ## Recommended Settings - **LoRA strength / weight:** `1.0` (the published samples used strength 1.0). - **Resolution & frames:** Trained and validated at **960×544×121 @ 24fps** (frames satisfy `(frames-1) % 8 == 0`). Both landscape (960×544) and portrait (544×960) were in training. Start near this bucket for the strongest, most consistent effect. - **Prompting:** Follow the `Reference shows … COLORIZE … only color information differs` structure documented in [How It Works](#how-it-works). Describe the same scene in both halves; only change the color description. Keep identity/framing/geometry language intact so the model only alters color. - **Production inference recipe (what we used):** Run via the distilled `ltx_pipelines.ic_lora` pipeline with the **identity-safe, stage-1-only native hi-res** recipe — render on a 2× canvas with `--skip-stage-2 --tile-reference-encode` (stage 2 is skipped so the reference stays anchored for the whole denoise), LoRA strength `1.0`, seed `42`, 121 frames @ 24fps. The distilled checkpoint uses fixed sigmas, so there is **no CFG / guidance scale and no negative prompt**. A dev-trained LoRA loads cleanly on the distilled checkpoint. ## References - **Code:** [GitHub Repository](https://github.com/Lightricks/LTX-2) - **Inference Pipeline:** `ltx_pipelines.ic_lora` (LTX-2 distilled IC-LoRA pipeline) ## Tips & Troubleshooting - **Weak or partial colorization at very high resolution:** the model generates stage-1 at the full output resolution, which is well above the 960×544 training bucket. If color looks washed out or incomplete, lower the generation/output resolution toward the training bucket. - **Color bleed or oversaturation:** drop the LoRA strength slightly (e.g. `0.8–0.9`) and make the `COLORIZE` description more specific about the intended hues. - **Identity drift:** keep the stage-1-only recipe (do not use the two-stage path for identity-critical clips) so the reference stays attached for the entire denoise. ## Dataset The model was trained using a proprietary dataset. ## Training - **Technique:** IC-LoRA (rank 128, alpha 128, dropout 0.05) on the DiT transformer; target modules `attn1.to_q`, `attn1.to_k`, `attn1.to_v`, `attn1.to_out.0`, `ff.net.0.proj`, `ff.net.2`. - **Hyperparameters:** bf16 mixed precision, AdamW optimizer, learning rate 1.5e-4, cosine scheduler, gradient checkpointing on, batch size 1. - **Steps:** 1500 total training steps configured. Released checkpoint: `ltx-2.5-22b-ic-lora-colorization-0.9.safetensors`. - **Infrastructure:** LTX-2 Community Trainer (single-node, 8 GPU). ## License See the **[LTX-2.x Community License](https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x)** for full terms. ## Acknowledgments - Base model by **[Lightricks](https://ltx.io/)** - Training infrastructure: **[LTX-2 Community Trainer](https://github.com/Lightricks/LTX-2/tree/main/packages/ltx-trainer)**