Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,217 @@
+---
+base_model:
+  - diffusers/LTX-2.3-Diffusers
+library_name: diffusers
+license: apache-2.0
+pipeline_tag: image-to-video
+tags:
+  - diffusers
+  - safetensors
+  - image-to-video
+  - text-to-video
+  - audio-video
+  - ltx-2-3
+  - vbvr
+datasets:
+  - Video-Reason/VBVR-Dataset
+---
+
+# VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
+
+<a href="https://video-reason.com/?v=pro" target="_blank">
+    <img alt="Project Page" src="https://img.shields.io/badge/Project%20-%20Homepage-4285F4" height="20" />
+</a>
+<a href="https://github.com/Video-Reason/VBVR-Pro-Bench" target="_blank">
+    <img alt="Code" src="https://img.shields.io/badge/Evaluation_code-VBVR_Pro_Bench-100000?style=flat-square&logo=github&logoColor=white" height="20" />
+</a>
+<a href="https://github.com/Video-Reason/VBVR-Pro" target="_blank">
+    <img alt="Code" src="https://img.shields.io/badge/Training_Inferenceing-VBVR_Pro-100000?style=flat-square&logo=github&logoColor=white" height="20" />
+</a>
+<a href="https://huggingface.co/papers/2602.20159" target="_blank">
+    <img alt="arXiv" src="https://img.shields.io/badge/arXiv-VBVR_Pro-red?logo=arxiv" height="20" />
+</a>
+<a href="https://huggingface.co/datasets/Video-Reason/VBVR-Pro-SFT-Video" target="_blank">
+    <img alt="Dataset" src="https://img.shields.io/badge/%F0%9F%A4%97%20_VBVR_Pro_Dataset-Data-ffc107?color=ffc107&logoColor=white" height="20" />
+</a>
+<a href="https://huggingface.co/datasets/Video-Reason/VBVR-Pro-Bench/tree/main" target="_blank">
+    <img alt="Bench Data" src="https://img.shields.io/badge/%F0%9F%A4%97%20_VBVR_Pro_Bench-Data-ffc107?color=ffc107&logoColor=white" height="20" />
+</a>
+<a href="https://video-reason.com/pro/bench/#leaderboard" target="_blank">
+    <img alt="Leaderboard" src="https://img.shields.io/badge/%F0%9F%A4%97%20_VBVR_Pro_Bench-Leaderboard-ffc107?color=ffc107&logoColor=white" height="20" />
+</a>
+
+## Overview
+Native visual reasoning, i.e., reasoning through visual generation, has recently emerged as a promising direction for studying visual intelligence beyond language. Yet progress remains bottlenecked by the lack of scalable training tasks, reliable feedback, and controlled comparisons across generative substrates. In this work, we introduce **VBVR-Pro**, a closed-loop testbed that makes native visual reasoning through generation trainable, verifiable, optimizable, and experimentally controllable. **1) Task scaling.** VBVR-Pro turns visual reasoning into a controlled task space of *300* procedurally generated tasks. Models trained on VBVR-Pro show strong transfer beyond the proposed suite across *six* held-out visual reasoning benchmarks such as RISE-Video, MME-CoF-Pro, and BabyVision. Further analysis validates that these gains reflect visual reasoning rather than instruction-pattern fitting. **2) Verifiable rewards.** VBVR-Pro provides verifiable reward scorers for task-grounded evaluation. Through a systematic study of leading MLLMs as judges, we identify recurring failure modes of the prevalent *VLM-as-a-judge* paradigm. In contrast, the proposed scorers are grounded on verifiable task-specific rules, achieve fine-grained alignment with human judgments. Importantly, they serve as reliable reward signals for large-scale multi-task reinforcement learning and demonstrate stronger post-RL performance across visual reasoning tasks. **3) Mechanism study.** VBVR-Pro enables controlled modality studies across more than *30* image, video, and interleaved generators. Our analysis shows that video generation remains strongest for tasks requiring persistent spatiotemporal state tracking, while interleaved generation provides a compute-efficient alternative by externalizing intermediate visual states. Critically, ablations and probing confirm the presence of vision-native trajectories, that are a more crucial substrate than explicit linguistic chains of thought for visual reasoning. We release all data, models, scorers, and code to facilitate future research.
+
+The models are presented in the paper [VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning](https://huggingface.co/papers/2602.20159).
+
+## Models Zoo
+<table border="1" cellspacing="0" cellpadding="4" style="border-collapse: collapse; width: 100%;">
+  <thead>
+    <tr>
+      <th width="260" style="min-width: 260px;">Model</th>
+      <th>Base Architecture</th>
+      <th>Other Remarks</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr style="border-top: 4px solid #6b7280; background-color: #e5e7eb;"><th colspan="3" align="left">Image Generation Models</th></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-BAGEL">VBVR-Pro-BAGEL</a></td><td>BAGEL-7B-MoT</td><td>Complete model</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-FLUX2-dev">VBVR-Pro-FLUX2-dev</a></td><td>FLUX.2-dev</td><td>Complete model, Diffusers format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-FLUX2-dev-diffsynth">VBVR-Pro-FLUX2-dev-diffsynth</a></td><td>FLUX.2-dev</td><td>LoRA model, DiffSynth format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-Qwen-Image-Edit">VBVR-Pro-Qwen-Image-Edit</a></td><td>Qwen-Image-Edit-2511</td><td>Complete model, Diffusers format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-Qwen-Image-Edit-diffsynth">VBVR-Pro-Qwen-Image-Edit-diffsynth</a></td><td>Qwen-Image-Edit-2511</td><td>LoRA model, DiffSynth format</td></tr>
+    <tr style="border-top: 4px solid #6b7280; background-color: #e5e7eb;"><th colspan="3" align="left">Interleaved Image Generation Models</th></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-ThinkMorph">VBVR-Pro-ThinkMorph</a></td><td>ThinkMorph-7B</td><td>Complete model</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-SenseNova-U1">VBVR-Pro-SenseNova-U1</a></td><td>SenseNova-U1-8B-MoT</td><td>Complete model</td></tr>
+    <tr style="border-top: 4px solid #6b7280; background-color: #e5e7eb;"><th colspan="3" align="left">Video Generation Models</th></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-LTX2.3"><strong>VBVR-Pro-LTX2.3</strong></a></td><td>LTX-Video-2.3</td><td>Complete model, Diffusers format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-LTX2.3-diffsynth">VBVR-Pro-LTX2.3-diffsynth</a></td><td>LTX-Video-2.3</td><td>LoRA model, DiffSynth format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-Wan2.1-I2V-14B">VBVR-Pro-Wan2.1-I2V-14B</a></td><td>Wan2.1-I2V-14B-720P</td><td>Complete model, Diffusers format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-Wan2.1-I2V-14B-diffsynth">VBVR-Pro-Wan2.1-I2V-14B-diffsynth</a></td><td>Wan2.1-I2V-14B-720P</td><td>LoRA model, DiffSynth format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-Wan2.2-I2V-A14B">VBVR-Pro-Wan2.2-I2V-A14B</a></td><td>Wan2.2-I2V-A14B</td><td>Complete model, Diffusers format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-Wan2.2-I2V-A14B-diffsynth">VBVR-Pro-Wan2.2-I2V-A14B-diffsynth</a></td><td>Wan2.2-I2V-A14B</td><td>LoRA model, DiffSynth format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-Wan2.2-TI2V-5B">VBVR-Pro-Wan2.2-TI2V-5B</a></td><td>Wan2.2-TI2V-5B</td><td>Complete model, Diffusers format</td></tr>
+    <tr><td><a href="https://huggingface.co/Video-Reason/VBVR-Pro-Wan2.2-TI2V-5B-diffsynth">VBVR-Pro-Wan2.2-TI2V-5B-diffsynth</a></td><td>Wan2.2-TI2V-5B</td><td>LoRA model, DiffSynth format</td></tr>
+  </tbody>
+</table>
+
+## Release Information
+
+VBVR-Pro fine-tuned **LTX-2.3** for instruction-based, image-conditioned
+audio-video generation. It was trained on the
+[VBVR-Dataset](https://huggingface.co/datasets/Video-Reason/VBVR-Dataset).
+
+This is the **merged model**: the rank-32 LoRA has already been fused into the
+LTX transformer weights. Load it directly with
+[diffusers](https://github.com/huggingface/diffusers); no adapter needs to be
+loaded separately.
+
+| Format | Repository |
+|---|---|
+| Merged / Diffusers (this repo) | `VBVR-Pro-LTX2.3` |
+| DiffSynth LoRA | `VBVR-Pro-LTX2.3-diffsynth` |
+
+In this release, we present all models presented in paper 
+[**VBVR-Pro-Trained-Models**](https://huggingface.co/collections/Video-Reason/VBVR-Pro),
+[**VBVR-Pro-Dataset-Video**](https://huggingface.co/datasets/Video-Reason/VBVR-Pro-SFT-Video),
+[**VBVR-Pro-Dataset-Image**](https://huggingface.co/datasets/Video-Reason/VBVR-Pro-SFT-Image),
+[**VBVR-Pro-Bench**](https://huggingface.co/datasets/Video-Reason/VBVR-Pro-Bench),
+[**VBVR-Pro-Code**](https://github.com/Video-Reason/VBVR-Pro) and 
+[**VBVR-Bench-Leaderboard**](https://video-reason.com/pro/bench/#leaderboard).
+
+## VBVR-Pro Benchmark Results
+<table border="1" cellspacing="0" cellpadding="4" style="border-collapse: collapse; width: 100%; font-size: 12px;">
+  <thead>
+    <tr>
+      <th rowspan="2" width="260" style="min-width: 260px;">Models</th>
+      <th rowspan="2">Overall</th>
+      <th colspan="6">In-Domain by Category</th>
+      <th colspan="6">Out-of-Domain by Category</th>
+    </tr>
+    <tr>
+      <th>Avg.</th><th>Abst.</th><th>Know.</th><th>Perc.</th><th>Spat.</th><th>Trans.</th>
+      <th>Avg.</th><th>Abst.</th><th>Know.</th><th>Perc.</th><th>Spat.</th><th>Trans.</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr style="border-top: 4px solid #6b7280; background-color: #e5e7eb;"><th colspan="14" align="left">Image Generation Models</th></tr>
+    <tr style="background-color: #dbeafe;"><th colspan="14" align="left">Proprietary Models</th></tr>
+    <tr><td>Qwen-Image-2.0</td><td><u>0.313</u></td><td><u>0.248</u></td><td><u>0.269</u></td><td><u>0.196</u></td><td><u>0.225</u></td><td><u>0.170</u></td><td><u>0.132</u></td><td><u>0.378</u></td><td><u>0.341</u></td><td><u>0.235</u></td><td><u>0.391</u></td><td><u>0.384</u></td><td><u>0.080</u></td></tr>
+    <tr><td>Seedream-5.0-Pro</td><td><strong>0.557</strong></td><td><strong>0.485</strong></td><td><strong>0.518</strong></td><td><strong>0.312</strong></td><td><strong>0.509</strong></td><td><strong>0.401</strong></td><td><strong>0.217</strong></td><td><strong>0.629</strong></td><td><strong>0.507</strong></td><td><strong>0.455</strong></td><td><strong>0.661</strong></td><td><strong>0.559</strong></td><td><strong>0.202</strong></td></tr>
+    <tr style="background-color: #dbeafe;"><th colspan="14" align="left">Open-source Models</th></tr>
+    <tr><td>BAGEL-7B-MoT</td><td>0.089</td><td><u>0.066</u></td><td>0.039</td><td><u>0.085</u></td><td>0.067</td><td>0.046</td><td>0.027</td><td>0.111</td><td><strong>0.201</strong></td><td>0.031</td><td>0.073</td><td>0.028</td><td><strong>0.121</strong></td></tr>
+    <tr><td>FLUX.2-dev</td><td><strong>0.157</strong></td><td><strong>0.108</strong></td><td><u>0.088</u></td><td><strong>0.109</strong></td><td><u>0.072</u></td><td><u>0.100</u></td><td><strong>0.066</strong></td><td><strong>0.206</strong></td><td><u>0.197</u></td><td><strong>0.165</strong></td><td><strong>0.184</strong></td><td><strong>0.241</strong></td><td>0.077</td></tr>
+    <tr><td>Qwen-Image-Edit</td><td><u>0.134</u></td><td><strong>0.108</strong></td><td><strong>0.092</strong></td><td>0.082</td><td><strong>0.100</strong></td><td><strong>0.109</strong></td><td><u>0.056</u></td><td><u>0.159</u></td><td>0.176</td><td><u>0.063</u></td><td><u>0.141</u></td><td><u>0.182</u></td><td><u>0.082</u></td></tr>
+    <tr style="background-color: #dbeafe;"><th colspan="14" align="left">Strong Baselines</th></tr>
+    <tr><td>VBVR-Pro-BAGEL</td><td>0.172</td><td>0.168</td><td>0.199</td><td>0.105</td><td>0.110</td><td>0.213</td><td>0.055</td><td>0.176</td><td>0.254</td><td>0.104</td><td>0.148</td><td>0.015</td><td><u>0.145</u></td></tr>
+    <tr><td>VBVR-Pro-FLUX.2</td><td><strong>0.407</strong></td><td><strong>0.484</strong></td><td><strong>0.483</strong></td><td><strong>0.323</strong></td><td><strong>0.367</strong></td><td><strong>0.449</strong></td><td><strong>0.336</strong></td><td><strong>0.330</strong></td><td><strong>0.361</strong></td><td><strong>0.272</strong></td><td><strong>0.255</strong></td><td><strong>0.454</strong></td><td>0.128</td></tr>
+    <tr><td>VBVR-Pro-Qwen-Image</td><td><u>0.322</u></td><td><u>0.332</u></td><td><u>0.298</u></td><td><u>0.217</u></td><td><u>0.193</u></td><td><u>0.431</u></td><td><u>0.222</u></td><td><u>0.311</u></td><td><u>0.341</u></td><td><u>0.239</u></td><td><u>0.233</u></td><td><u>0.413</u></td><td><strong>0.181</strong></td></tr>
+    <tr style="border-top: 4px solid #6b7280; background-color: #e5e7eb;"><th colspan="14" align="left">Interleaved Image Generation Models</th></tr>
+    <tr style="background-color: #dbeafe;"><th colspan="14" align="left">Proprietary Models</th></tr>
+    <tr><td>GPT-Image-2</td><td><u>0.507</u></td><td><u>0.428</u></td><td><u>0.456</u></td><td><u>0.318</u></td><td><u>0.428</u></td><td><u>0.206</u></td><td><strong>0.300</strong></td><td><u>0.587</u></td><td><u>0.398</u></td><td><u>0.413</u></td><td><u>0.633</u></td><td><u>0.480</u></td><td><strong>0.303</strong></td></tr>
+    <tr><td>Nano Banana Pro</td><td><strong>0.564</strong></td><td><strong>0.480</strong></td><td><strong>0.518</strong></td><td><strong>0.422</strong></td><td><strong>0.512</strong></td><td><strong>0.285</strong></td><td><u>0.174</u></td><td><strong>0.648</strong></td><td><strong>0.553</strong></td><td><strong>0.499</strong></td><td><strong>0.657</strong></td><td><strong>0.585</strong></td><td><u>0.220</u></td></tr>
+    <tr style="background-color: #dbeafe;"><th colspan="14" align="left">Open-source Models</th></tr>
+    <tr><td>ThinkMorph-7B</td><td>0.154</td><td>0.113</td><td>0.100</td><td>0.082</td><td>0.101</td><td>0.148</td><td>0.031</td><td>0.195</td><td>0.176</td><td>0.166</td><td>0.163</td><td>0.253</td><td>0.103</td></tr>
+    <tr><td>VBVR-SenseNova-U1</td><td><u>0.408</u></td><td><u>0.469</u></td><td><u>0.356</u></td><td><u>0.313</u></td><td><u>0.373</u></td><td><strong>0.386</strong></td><td><strong>0.477</strong></td><td><u>0.347</u></td><td><u>0.291</u></td><td><u>0.317</u></td><td><u>0.275</u></td><td><u>0.480</u></td><td><u>0.238</u></td></tr>
+    <tr><td>SenseNova-U1-8B-MoT</td><td><strong>0.565</strong></td><td><strong>0.533</strong></td><td><strong>0.501</strong></td><td><strong>0.395</strong></td><td><strong>0.544</strong></td><td><u>0.355</u></td><td><u>0.349</u></td><td><strong>0.597</strong></td><td><strong>0.448</strong></td><td><strong>0.495</strong></td><td><strong>0.533</strong></td><td><strong>0.717</strong></td><td><strong>0.401</strong></td></tr>
+    <tr style="background-color: #dbeafe;"><th colspan="14" align="left">Strong Baselines</th></tr>
+    <tr><td>VBVR-Pro-ThinkMorph</td><td><u>0.373</u></td><td><u>0.402</u></td><td><u>0.403</u></td><td><u>0.344</u></td><td><u>0.238</u></td><td><u>0.454</u></td><td><u>0.184</u></td><td><u>0.344</u></td><td><u>0.367</u></td><td><u>0.224</u></td><td><u>0.238</u></td><td><u>0.535</u></td><td><u>0.257</u></td></tr>
+    <tr><td>VBVR-Pro-SenseNova-U1</td><td><strong>0.638</strong></td><td><strong>0.811</strong></td><td><strong>0.648</strong></td><td><strong>0.695</strong></td><td><strong>0.621</strong></td><td><strong>0.770</strong></td><td><strong>0.541</strong></td><td><strong>0.464</strong></td><td><strong>0.480</strong></td><td><strong>0.328</strong></td><td><strong>0.344</strong></td><td><strong>0.558</strong></td><td><strong>0.408</strong></td></tr>
+    <tr style="border-top: 4px solid #6b7280; background-color: #e5e7eb;"><th colspan="14" align="left">Video Generation Models</th></tr>
+    <tr style="background-color: #dbeafe;"><th colspan="14" align="left">Proprietary Models</th></tr>
+    <tr><td>Veo 3.1</td><td>0.309</td><td>0.312</td><td><u>0.275</u></td><td>0.299</td><td>0.252</td><td>0.267</td><td>0.157</td><td>0.305</td><td><u>0.305</u></td><td>0.233</td><td>0.252</td><td><u>0.312</u></td><td>0.219</td></tr>
+    <tr><td>Kling V3</td><td><u>0.392</u></td><td><u>0.356</u></td><td>0.213</td><td><u>0.326</u></td><td><u>0.320</u></td><td><u>0.355</u></td><td><u>0.229</u></td><td><u>0.427</u></td><td>0.294</td><td><strong>0.564</strong></td><td><u>0.375</u></td><td>0.242</td><td><u>0.412</u></td></tr>
+    <tr><td>SeedDance 2.0</td><td><strong>0.499</strong></td><td><strong>0.451</strong></td><td><strong>0.338</strong></td><td><strong>0.361</strong></td><td><strong>0.353</strong></td><td><strong>0.468</strong></td><td><strong>0.308</strong></td><td><strong>0.547</strong></td><td><strong>0.369</strong></td><td><u>0.511</u></td><td><strong>0.478</strong></td><td><strong>0.538</strong></td><td><strong>0.532</strong></td></tr>
+    <tr style="background-color: #dbeafe;"><th colspan="14" align="left">Open-source Models</th></tr>
+    <tr><td>HunyuanVideo-I2V</td><td>0.054</td><td>0.054</td><td>0.023</td><td>0.064</td><td>0.015</td><td>0.084</td><td>0.032</td><td>0.053</td><td>0.088</td><td>0.014</td><td>0.028</td><td>0.062</td><td>0.055</td></tr>
+    <tr><td>CogVideoX1.5-5B-I2V</td><td>0.085</td><td>0.100</td><td>0.061</td><td>0.118</td><td>0.069</td><td>0.092</td><td>0.060</td><td>0.070</td><td>0.125</td><td>0.038</td><td>0.051</td><td>0.040</td><td>0.024</td></tr>
+    <tr><td>Wan2.1-I2V-14B</td><td>0.100</td><td>0.105</td><td>0.052</td><td>0.125</td><td>0.091</td><td>0.102</td><td>0.052</td><td>0.095</td><td>0.112</td><td>0.073</td><td>0.071</td><td>0.123</td><td>0.044</td></tr>
+    <tr><td>Wan2.2-TI2V-5B</td><td>0.094</td><td>0.066</td><td>0.029</td><td>0.073</td><td>0.050</td><td>0.083</td><td>0.031</td><td>0.122</td><td>0.156</td><td>0.052</td><td>0.106</td><td>0.063</td><td>0.099</td></tr>
+    <tr><td>Wan2.2-I2V-14B-720P</td><td><u>0.182</u></td><td><u>0.157</u></td><td><u>0.082</u></td><td><u>0.131</u></td><td><u>0.110</u></td><td><u>0.161</u></td><td><u>0.156</u></td><td><u>0.207</u></td><td><u>0.224</u></td><td><u>0.139</u></td><td><u>0.140</u></td><td><u>0.195</u></td><td><u>0.273</u></td></tr>
+    <tr><td>LTX2.3-I2AV</td><td>0.112</td><td>0.106</td><td>0.062</td><td>0.109</td><td>0.070</td><td>0.133</td><td>0.055</td><td>0.119</td><td>0.161</td><td>0.135</td><td>0.086</td><td>0.091</td><td>0.050</td></tr>
+    <tr><td>VBVR-Wan2.2</td><td><strong>0.517</strong></td><td><strong>0.548</strong></td><td><strong>0.237</strong></td><td><strong>0.499</strong></td><td><strong>0.334</strong></td><td><strong>0.566</strong></td><td><strong>0.591</strong></td><td><strong>0.486</strong></td><td><strong>0.310</strong></td><td><strong>0.343</strong></td><td><strong>0.345</strong></td><td><strong>0.732</strong></td><td><strong>0.684</strong></td></tr>
+    <tr style="background-color: #dbeafe;"><th colspan="14" align="left">Strong Baselines</th></tr>
+    <tr><td>VBVR-Pro-LTX2.3</td><td>0.425</td><td>0.527</td><td>0.409</td><td>0.510</td><td>0.346</td><td>0.460</td><td>0.390</td><td>0.324</td><td>0.381</td><td>0.108</td><td>0.201</td><td>0.477</td><td>0.386</td></tr>
+    <tr><td>VBVR-Pro-Wan2.1-I2V-14B</td><td><u>0.562</u></td><td><u>0.730</u></td><td><u>0.617</u></td><td><u>0.580</u></td><td><u>0.452</u></td><td><u>0.676</u></td><td><u>0.623</u></td><td><u>0.395</u></td><td><u>0.410</u></td><td><u>0.305</u></td><td><u>0.230</u></td><td><u>0.617</u></td><td><u>0.439</u></td></tr>
+    <tr><td>VBVR-Pro-Wan2.2-TI2V-5B</td><td>0.470</td><td>0.641</td><td>0.528</td><td>0.556</td><td>0.373</td><td>0.565</td><td>0.557</td><td>0.300</td><td>0.333</td><td>0.127</td><td>0.161</td><td>0.505</td><td>0.409</td></tr>
+    <tr><td>VBVR-Pro-Wan2.2-I2V-14B</td><td><strong>0.670</strong></td><td><strong>0.808</strong></td><td><strong>0.632</strong></td><td><strong>0.685</strong></td><td><strong>0.556</strong></td><td><strong>0.751</strong></td><td><strong>0.636</strong></td><td><strong>0.532</strong></td><td><strong>0.479</strong></td><td><strong>0.418</strong></td><td><strong>0.350</strong></td><td><strong>0.679</strong></td><td><strong>0.690</strong></td></tr>
+  </tbody>
+</table>
+
+## Quick Start
+
+### Method 1: Standalone Diffusers inference
+
+#### 1. Install Diffusers
+
+```bash
+pip install -U diffusers transformers accelerate pillow imageio imageio-ffmpeg
+```
+
+#### 2. Run `example.py`
+
+The included [`example.py`](example.py) loads the merged checkpoint directly
+with Diffusers, enables model CPU offloading, and writes synchronized audio and
+video to an MP4 file.
+
+```bash
+python example.py \
+  --model_path Video-Reason/VBVR-Pro-LTX2.3 \
+  --image input.png \
+  --prompt "The machine starts and makes a quiet mechanical hum." \
+  --num_frames 49 --fps 24 \
+  --output output.mp4
+```
+
+### Method 2: Unified VBVR-Pro inference
+
+Clone [Video-Reason/VBVR-Pro](https://github.com/Video-Reason/VBVR-Pro) and
+create its unified inference environment:
+
+```bash
+git clone https://github.com/Video-Reason/VBVR-Pro.git
+cd VBVR-Pro/
+uv sync --extra cu124 # or one of [cu118|cu121|cu124|cu126|cu128|cu129]
+source .venv/bin/activate
+```
+
+Then run the unified inference script:
+
+```bash
+python example.py \
+  --model_path Video-Reason/VBVR-Pro-LTX2.3 \
+  --image_paths input.png \
+  --prompt "The machine starts and makes a quiet mechanical hum." \
+  --num_frames 49 --fps 24 \
+  --output output.mp4
+```
+
+## Citation
+
+```bibtex
+@article{vbvr2025,
+  title={VBVR: A Very Big Video Reasoning Suite},
+  year={2025},
+}
+```

audio_vae/config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "AutoencoderKLLTX2Audio",
+  "_diffusers_version": "0.37.0.dev0",
+  "attn_resolutions": null,
+  "base_channels": 128,
+  "causality_axis": "height",
+  "ch_mult": [
+    1,
+    2,
+    4
+  ],
+  "double_z": true,
+  "dropout": 0.0,
+  "in_channels": 2,
+  "is_causal": true,
+  "latent_channels": 8,
+  "mel_bins": 64,
+  "mel_hop_length": 160,
+  "mid_block_add_attention": false,
+  "norm_type": "pixel",
+  "num_res_blocks": 2,
+  "output_channels": 2,
+  "resolution": 256,
+  "sample_rate": 16000
+}

audio_vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dcb1c3cffc8c8b7710a04dd19500e481daff31f5ea8e8529f2cf697c439d12
+size 106507972

connectors/config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "LTX2TextConnectors",
+  "_diffusers_version": "0.37.0.dev0",
+  "audio_connector_attention_head_dim": 64,
+  "audio_connector_num_attention_heads": 32,
+  "audio_connector_num_layers": 8,
+  "audio_connector_num_learnable_registers": 128,
+  "audio_gated_attn": true,
+  "audio_hidden_dim": 2048,
+  "caption_channels": 3840,
+  "causal_temporal_positioning": false,
+  "connector_rope_base_seq_len": 4096,
+  "per_modality_projections": true,
+  "proj_bias": true,
+  "rope_double_precision": true,
+  "rope_theta": 10000.0,
+  "rope_type": "split",
+  "text_proj_in_factor": 49,
+  "video_connector_attention_head_dim": 128,
+  "video_connector_num_attention_heads": 32,
+  "video_connector_num_layers": 8,
+  "video_connector_num_learnable_registers": 128,
+  "video_gated_attn": true,
+  "video_hidden_dim": 4096
+}

connectors/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b767a411e336d692306d7d34fa85627db1d17809a4690f45dd96a4b3807d248c
+size 4999998520

connectors/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe33521b2bbd12604abe2d63b5cf02cf55f2fdf10226ff5aae00e437678ebc8
+size 1344490576

connectors/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,269 @@
+{
+  "metadata": {
+    "total_size": 6344455168
+  },
+  "weight_map": {
+    "audio_connector.learnable_registers": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_connector.transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "audio_text_proj_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "audio_text_proj_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.learnable_registers": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.0.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.1.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.2.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.3.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.4.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.ff.net.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.5.ff.net.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_k.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_out.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_q.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_v.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.attn1.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.ff.net.0.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.ff.net.0.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.6.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_gate_logits.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_gate_logits.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_k.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_out.0.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_q.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_v.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.attn1.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.ff.net.0.proj.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.ff.net.0.proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.ff.net.2.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_connector.transformer_blocks.7.ff.net.2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "video_text_proj_in.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "video_text_proj_in.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
+  }
+}

example.py

@@ -0,0 +1,65 @@
+"""VBVR-Pro-LTX2.3 image-to-audio-video inference example.
+
+Usage:
+    python example.py --model_path Video-Reason/VBVR-Pro-LTX2.3 \
+        --image input.png --prompt "Your video instruction"
+"""
+
+import argparse
+
+import torch
+from diffusers import LTX2ImageToVideoPipeline
+from diffusers.utils import encode_video, load_image
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--model_path", type=str, default="Video-Reason/VBVR-Pro-LTX2.3")
+parser.add_argument("--image", type=str, required=True, help="Path or URL to input image")
+parser.add_argument("--prompt", type=str, required=True, help="Video instruction")
+parser.add_argument(
+    "--negative_prompt",
+    type=str,
+    default="blurry, low quality, flickering, motion blur, distorted",
+)
+parser.add_argument("--output", type=str, default="output.mp4")
+parser.add_argument("--width", type=int, default=768)
+parser.add_argument("--height", type=int, default=512)
+parser.add_argument("--num_frames", type=int, default=49)
+parser.add_argument("--steps", type=int, default=40)
+parser.add_argument("--guidance_scale", type=float, default=5.0)
+parser.add_argument("--fps", type=int, default=24)
+parser.add_argument("--seed", type=int, default=42)
+args = parser.parse_args()
+
+print(f"Loading model from: {args.model_path}")
+pipe = LTX2ImageToVideoPipeline.from_pretrained(
+    args.model_path, torch_dtype=torch.bfloat16
+)
+pipe.enable_model_cpu_offload()
+
+image = load_image(args.image).convert("RGB")
+print(f"Input image: {args.image} ({image.size[0]}x{image.size[1]})")
+
+video, audio = pipe(
+    image=image,
+    prompt=args.prompt,
+    negative_prompt=args.negative_prompt,
+    height=args.height,
+    width=args.width,
+    num_frames=args.num_frames,
+    frame_rate=args.fps,
+    num_inference_steps=args.steps,
+    guidance_scale=args.guidance_scale,
+    generator=torch.manual_seed(args.seed),
+    output_type="np",
+    return_dict=False,
+)
+
+encode_video(
+    video[0][: args.num_frames],
+    fps=args.fps,
+    output_path=args.output,
+    audio=audio[0].float().cpu(),
+    audio_sample_rate=pipe.vocoder.config.output_sampling_rate,
+)
+print(f"Saved to: {args.output}")

model_index.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "LTX2Pipeline",
+  "_diffusers_version": "0.37.0.dev0",
+  "audio_vae": [
+    "diffusers",
+    "AutoencoderKLLTX2Audio"
+  ],
+  "connectors": [
+    "ltx2",
+    "LTX2TextConnectors"
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Gemma3ForConditionalGeneration"
+  ],
+  "tokenizer": [
+    "transformers",
+    "GemmaTokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "LTX2VideoTransformer3DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLLTX2Video"
+  ],
+  "vocoder": [
+    "ltx2",
+    "LTX2VocoderWithBWE"
+  ]
+}

processor/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

processor/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

processor/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

processor/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

processor/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

processor/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.37.0.dev0",
+  "base_image_seq_len": 1024,
+  "base_shift": 0.95,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 2.05,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": 0.1,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,114 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "dtype": "float32",
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "_sliding_window_pattern": 6,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "dtype": "float32",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "transformers_version": "4.57.3",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

text_encoder/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

text_encoder/model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc6e8132e4998652d4c8c219f0ca8da10a143606c806c8728a7513d49bbcdb3
+size 1685223128

text_encoder/model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b95e7ab472b88860e53c71ef078fe8ba4c85e3727b8f0a0bcc130c1f4a2b9ab9
+size 4987027384

text_encoder/model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3731e7c18280d0e9dcbcfadaecaeb8b81fa7f7f15e702ea3d1b4f8eb1b5919f7
+size 4844749824

text_encoder/model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d1ce8b472f2cc6d70c7885388f50fb3a5f233cf1d4784f6a4be1732547a74c
+size 4954909736

text_encoder/model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb478659a67b2e34a920f237387a1d7a8208325aa2fc285198a97603f15af1e6
+size 4907664584

text_encoder/model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a190581d871980f9309f40d5c2b4db99d76737d7ed743d531bac95443f6b7145
+size 4954909792

text_encoder/model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c347de789ff34be642e4fe7ab8e142ca5e3d833d70cb9ec5127a86af0e2ecfed
+size 4907664584

text_encoder/model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ec7525b89b083d774f4abbdd1f2d7ee190f0475658875cf700530a2faa84a4f
+size 4954909792

text_encoder/model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0117ecf1d83691bb875c66a9f2b47e450a87fdfe90915bc7b9e9946c37a650
+size 4907664584

text_encoder/model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f665a743589231adb812c61c9d8e295c9a68c31d3e87976ae032f1de4e46b6
+size 4954909792

text_encoder/model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999bf4706d4f616e558eec486667fc2b66f8d0f9c106e1d1f802458fb349b0db
+size 2689808472

tokenizer/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

tokenizer/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

tokenizer/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

transformer/config.json

@@ -0,0 +1,50 @@
+{
+  "_class_name": "LTX2VideoTransformer3DModel",
+  "_diffusers_version": "0.37.0.dev0",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 128,
+  "attention_out_bias": true,
+  "audio_attention_head_dim": 64,
+  "audio_cross_attention_dim": 2048,
+  "audio_cross_attn_mod": true,
+  "audio_gated_attn": true,
+  "audio_hop_length": 160,
+  "audio_in_channels": 128,
+  "audio_num_attention_heads": 32,
+  "audio_out_channels": 128,
+  "audio_patch_size": 1,
+  "audio_patch_size_t": 1,
+  "audio_pos_embed_max_pos": 20,
+  "audio_sampling_rate": 16000,
+  "audio_scale_factor": 4,
+  "base_height": 2048,
+  "base_width": 2048,
+  "caption_channels": 3840,
+  "causal_offset": 1,
+  "cross_attention_dim": 4096,
+  "cross_attn_mod": true,
+  "cross_attn_timestep_scale_multiplier": 1000,
+  "gated_attn": true,
+  "in_channels": 128,
+  "norm_elementwise_affine": false,
+  "norm_eps": 1e-06,
+  "num_attention_heads": 32,
+  "num_layers": 48,
+  "out_channels": 128,
+  "patch_size": 1,
+  "patch_size_t": 1,
+  "perturbed_attn": true,
+  "pos_embed_max_pos": 20,
+  "qk_norm": "rms_norm_across_heads",
+  "rope_double_precision": true,
+  "rope_theta": 10000.0,
+  "rope_type": "split",
+  "timestep_scale_multiplier": 1000,
+  "use_prompt_embeddings": false,
+  "vae_scale_factors": [
+    8,
+    32,
+    32
+  ]
+}

transformer/diffusion_pytorch_model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56d3fe084a34b09705a26fb7b8afe319305589d1c034c9da1cd8df1e802b4195
+size 4990709464

transformer/diffusion_pytorch_model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475c1864d130da721d65063ef5f9a7b87f592b0fa82a1895bbb3498ae5729b84
+size 4944487248

transformer/diffusion_pytorch_model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1490bd335b22a82a39483d529b9b36d14c8e33e93022e791a67cbce2333e48
+size 4994661712

transformer/diffusion_pytorch_model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef755b082e189e29acc816513a1102d393b6f9d3885bc43826d7f4203be107fc
+size 4927859352

transformer/diffusion_pytorch_model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44ce733d707dfd594046829ed53400b192c77715cc44e47186054b8cb633e71
+size 4977604280

transformer/diffusion_pytorch_model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c3608162c0c5c8202552dcf7f3fd81a0fd13f7ec4616ed7184c8308daa1b34
+size 4994844576

transformer/diffusion_pytorch_model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b843ebeea2a5e80dd81736c63de83da83d7d472fca62200c6773902c58ed41
+size 4994386864

transformer/diffusion_pytorch_model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e0201d8630c6c0b8fea1752eb9d8ebe7272c01e7b6c206c7b9e78ece42ce2e
+size 3163094784