NVIDIA · aidanfnv · Aug 3, 2026 · Aug 3, 2026
diff --git a/docs/source/_static/model_clips/causal_forcing/causal-forcing-wan2.1-i2v-1.3b-framewise.avif b/docs/source/_static/model_clips/causal_forcing/causal-forcing-wan2.1-i2v-1.3b-framewise.avif
diff --git a/docs/source/_static/model_clips/causal_forcing/causal-forcing-wan2.1-t2v-1.3b-framewise.avif b/docs/source/_static/model_clips/causal_forcing/causal-forcing-wan2.1-t2v-1.3b-framewise.avif
diff --git a/docs/source/_static/model_clips/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_1.avif b/docs/source/_static/model_clips/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_1.avif
diff --git a/docs/source/_static/model_clips/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_2.avif b/docs/source/_static/model_clips/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_2.avif
diff --git a/docs/source/_static/model_clips/cosmos_predict2/cosmos-predict.avif b/docs/source/_static/model_clips/cosmos_predict2/cosmos-predict.avif
diff --git a/docs/source/_static/model_clips/cosmos_predict2/cosmos2-i2v-2b-720p.avif b/docs/source/_static/model_clips/cosmos_predict2/cosmos2-i2v-2b-720p.avif
diff --git a/docs/source/_static/model_clips/cosmos_predict2/cosmos2-t2v-2b-720p.avif b/docs/source/_static/model_clips/cosmos_predict2/cosmos2-t2v-2b-720p.avif
diff --git a/docs/source/_static/model_clips/flashvsr/example1.avif b/docs/source/_static/model_clips/flashvsr/example1.avif
diff --git a/docs/source/_static/model_clips/flashvsr/flashvsr-v1.1-sparse-ratio-2.0.avif b/docs/source/_static/model_clips/flashvsr/flashvsr-v1.1-sparse-ratio-2.0.avif
diff --git a/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-hero.avif b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-hero.avif
diff --git a/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-1.avif b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-1.avif
diff --git a/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-2.avif b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-2.avif
diff --git a/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-4.avif b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-4.avif
diff --git a/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-8.avif b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-8.avif
diff --git a/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-9.avif b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-9.avif
diff --git a/docs/source/_static/model_clips/lingbot_world/lingbot-world-fast-01.avif b/docs/source/_static/model_clips/lingbot_world/lingbot-world-fast-01.avif
diff --git a/docs/source/_static/model_clips/lingbot_world/lingbot-world-fast-02.avif b/docs/source/_static/model_clips/lingbot_world/lingbot-world-fast-02.avif
diff --git a/docs/source/_static/model_clips/lingbot_world/lingbot-world-teaser.avif b/docs/source/_static/model_clips/lingbot_world/lingbot-world-teaser.avif
diff --git a/docs/source/_static/model_clips/lingbot_world/lingbot-world-traj-01.avif b/docs/source/_static/model_clips/lingbot_world/lingbot-world-traj-01.avif
diff --git a/docs/source/_static/model_clips/lingbot_world/lingbot-world-traj-02.avif b/docs/source/_static/model_clips/lingbot_world/lingbot-world-traj-02.avif
diff --git a/docs/source/_static/model_clips/lingbot_world/lingbot-world-webrtc-recording-0529.avif b/docs/source/_static/model_clips/lingbot_world/lingbot-world-webrtc-recording-0529.avif
diff --git a/...ams-sv-2steps-chunk2-loc6-lightvae-lighttae-239560dc-33d1-11ef-9720-00044bcbccac-pip.avif b/...ams-sv-2steps-chunk2-loc6-lightvae-lighttae-239560dc-33d1-11ef-9720-00044bcbccac-pip.avif
diff --git a/...ams-sv-2steps-chunk2-loc6-lightvae-lighttae-24b84744-4156-11ef-b27d-00044bf655de-pip.avif b/...ams-sv-2steps-chunk2-loc6-lightvae-lighttae-24b84744-4156-11ef-b27d-00044bf655de-pip.avif
diff --git a/docs/source/_static/model_clips/omnidreams/omnidreams-teaser.avif b/docs/source/_static/model_clips/omnidreams/omnidreams-teaser.avif
diff --git a/docs/source/_static/model_clips/omnidreams/omnidreams-webrtc-recording-0529.avif b/docs/source/_static/model_clips/omnidreams/omnidreams-webrtc-recording-0529.avif
diff --git a/docs/source/_static/model_clips/self_forcing/self-forcing-wan2.1-t2v-1.3b-flash_1.avif b/docs/source/_static/model_clips/self_forcing/self-forcing-wan2.1-t2v-1.3b-flash_1.avif
diff --git a/docs/source/_static/model_clips/self_forcing/self-forcing-wan2.1-t2v-1.3b-flash_6.avif b/docs/source/_static/model_clips/self_forcing/self-forcing-wan2.1-t2v-1.3b-flash_6.avif
diff --git a/docs/source/_static/model_clips/wan21/wan21-i2v-14b-480p.avif b/docs/source/_static/model_clips/wan21/wan21-i2v-14b-480p.avif
diff --git a/docs/source/_static/model_clips/wan21/wan21-t2v-1.3b-480p.avif b/docs/source/_static/model_clips/wan21/wan21-t2v-1.3b-480p.avif
diff --git a/docs/source/models/causal_forcing.rst b/docs/source/models/causal_forcing.rst
@@ -131,19 +131,13 @@ Some generated samples from the above commands:
 
    <div class="model-video-grid zoomable">
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/causal_forcing/causal-forcing-wan2.1-t2v-1.3b-framewise.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/causal_forcing/causal-forcing-wan2.1-t2v-1.3b-framewise.avif" alt="Causal-Forcing text-to-video sample clip.">
        <div class="model-video-overlay">
          prompt: "A cinematic closeup and detailed portrait of a reindeer standing in a snowy forest at sunset. The lighting is gorgeous and soft, with a golden backlight creating a warm and dreamy effect. Soft bokeh and lens flares add a magical touch, enhancing the cinematic quality of the image. The reindeer has a gentle expression, its fur glistening in the fading light. The background features a serene snowy landscape with tall trees silhouetted against the orange and pink hues of the setting sun. The color grade is rich and magical, capturing the essence of a winter wonderland at twilight. A close-up shot from a slightly elevated angle."
        </div>
      </div>
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/causal_forcing/causal-forcing-wan2.1-i2v-1.3b-framewise.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/causal_forcing/causal-forcing-wan2.1-i2v-1.3b-framewise.avif" alt="Causal-Forcing image-to-video sample clip.">
        <div class="model-video-overlay">
          prompt: "A cinematic closeup and detailed portrait of a reindeer standing in a snowy forest at sunset. The lighting is gorgeous and soft, with a golden backlight creating a warm and dreamy effect. Soft bokeh and lens flares add a magical touch, enhancing the cinematic quality of the image. The reindeer has a gentle expression, its fur glistening in the fading light. The background features a serene snowy landscape with tall trees silhouetted against the orange and pink hues of the setting sun. The color grade is rich and magical, capturing the essence of a winter wonderland at twilight. A close-up shot from a slightly elevated angle."
          <br/>

diff --git a/docs/source/models/causal_wan22.rst b/docs/source/models/causal_wan22.rst
@@ -104,19 +104,13 @@ Some generated samples from the above commands:
 
    <div class="model-video-grid zoomable">
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_1.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_1.avif" alt="Causal Wan 2.2 Tokyo street sample clip.">
        <div class="model-video-overlay">
          prompt: "A stylish woman strolls down a bustling Tokyo street, the warm glow of neon lights and animated city signs casting vibrant reflections. She wears a sleek black leather jacket paired with a flowing red dress and black boots, her black purse slung over her shoulder. Sunglasses perched on her nose and a bold red lipstick add to her confident, casual demeanor. The street is damp and reflective, creating a mirror-like effect that enhances the colorful lights and shadows. Pedestrians move about, adding to the lively atmosphere. The scene is captured in a dynamic medium shot with the woman walking slightly to one side, highlighting her graceful strides."
        </div>
      </div>
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_2.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_2.avif" alt="Causal Wan 2.2 electronic guitar sample clip.">
        <div class="model-video-overlay">
          prompt: "A playful raccoon is seen playing an electronic guitar, strumming the strings with its front paws. The raccoon has distinctive black facial markings and a bushy tail. It sits comfortably on a small stool, its body slightly tilted as it focuses intently on the instrument. The setting is a cozy, dimly lit room with vintage posters on the walls, adding a retro vibe. The raccoon's expressive eyes convey a sense of joy and concentration. Medium close-up shot, focusing on the raccoon's face and hands interacting with the guitar."
        </div>

diff --git a/docs/source/models/cosmos_predict2.rst b/docs/source/models/cosmos_predict2.rst
@@ -46,18 +46,16 @@ reasoning vision language model - as its text encoder. The model is shipped in
 through a curated 200M-clip pre-training corpus, model merging, and a new RL
 algorithm.
 
-.. raw:: html
+.. container:: model-video-card model-hero-media zoomable
 
-   <div class="model-video-card" style="width: 100%; margin: 10px auto 14px;">
-     <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-       <source src="https://images.nvidia.com/aem-dam/Solutions/cosmos/cosmos-predict.mp4" type="video/mp4">
-       Your browser does not support the video tag.
-     </video>
-   </div>
-   <p class="model-footnote">
-     Teaser video source:
-     <a href="https://research.nvidia.com/labs/cosmos-lab/cosmos-predict2.5/">Cosmos-Predict2.5 project page</a>.
-   </p>
+   .. image:: /_static/model_clips/cosmos_predict2/cosmos-predict.avif
+      :alt: Cosmos-Predict2.5 teaser clip.
+      :class: model-video-player
+
+.. rst-class:: model-footnote
+
+Teaser video source:
+`Cosmos-Predict2.5 project page <https://research.nvidia.com/labs/cosmos-lab/cosmos-predict2.5/>`_.
 
 Requirements
 ------------
@@ -134,19 +132,13 @@ Some generated samples from the above commands:
 
    <div class="model-video-grid zoomable">
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/cosmos_predict2/cosmos2-t2v-2b-720p.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/cosmos_predict2/cosmos2-t2v-2b-720p.avif" alt="Cosmos-Predict2.5 text-to-video sample clip.">
        <div class="model-video-overlay">
          prompt: "A high-definition video captures the precision of robotic welding in an industrial setting. The first frame showcases a robotic arm, equipped with a welding torch, positioned over a large metal structure. The welding process is in full swing, with bright sparks and intense light illuminating the scene, creating a vivid display of blue and white hues. A significant amount of smoke billows around the welding area, partially obscuring the view but emphasizing the heat and activity. The background reveals parts of the workshop environment, including a ventilation system and various pieces of machinery, indicating a busy and functional industrial workspace. As the video progresses, the robotic arm maintains its steady position, continuing the welding process and moving to its left. The welding torch consistently emits sparks and light, and the smoke continues to rise, diffusing slightly as it moves upward. The metal surface beneath the torch shows ongoing signs of heating and melting. The scene retains its industrial ambiance, with the welding sparks and smoke dominating the visual field, underscoring the ongoing nature of the welding operation."
        </div>
      </div>
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/cosmos_predict2/cosmos2-i2v-2b-720p.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/cosmos_predict2/cosmos2-i2v-2b-720p.avif" alt="Cosmos-Predict2.5 image-to-video sample clip.">
        <div class="model-video-overlay">
          prompt: "A high-definition video captures the precision of robotic welding in an industrial setting. The first frame showcases a robotic arm, equipped with a welding torch, positioned over a large metal structure. The welding process is in full swing, with bright sparks and intense light illuminating the scene, creating a vivid display of blue and white hues. A significant amount of smoke billows around the welding area, partially obscuring the view but emphasizing the heat and activity. The background reveals parts of the workshop environment, including a ventilation system and various pieces of machinery, indicating a busy and functional industrial workspace. As the video progresses, the robotic arm maintains its steady position, continuing the welding process and moving to its left. The welding torch consistently emits sparks and light, and the smoke continues to rise, diffusing slightly as it moves upward. The metal surface beneath the torch shows ongoing signs of heating and melting. The scene retains its industrial ambiance, with the welding sparks and smoke dominating the visual field, underscoring the ongoing nature of the welding operation."
          <br/>

diff --git a/docs/source/models/flashvsr.rst b/docs/source/models/flashvsr.rst
@@ -123,14 +123,8 @@ A generated sample from the above commands:
 .. raw:: html
 
    <div class="model-video-card" style="width: 100%; margin: 10px auto 14px;">
-     <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-       <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/flashvsr/flashvsr-v1.1-sparse-ratio-2.0.mp4" type="video/mp4">
-       Your browser does not support the video tag.
-     </video>
-     <video autoplay muted loop playsinline preload="metadata" style="position: absolute; left: 10px; bottom: 10px; width: 50%; border: 2px solid rgba(255, 255, 255, 0.9); border-radius: 8px; box-shadow: 0 2px 10px rgba(0, 0, 0, 0.5); pointer-events: none;">
-       <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/flashvsr/example1.mp4" type="video/mp4">
-       Your browser does not support the video tag.
-     </video>
+     <img class="model-video-player" src="../_static/model_clips/flashvsr/flashvsr-v1.1-sparse-ratio-2.0.avif" alt="FlashVSR output sample clip.">
+     <img src="../_static/model_clips/flashvsr/example1.avif" alt="FlashVSR low-resolution input inset." style="position: absolute; left: 10px; bottom: 10px; width: 50%; border: 2px solid rgba(255, 255, 255, 0.9); border-radius: 8px; box-shadow: 0 2px 10px rgba(0, 0, 0, 0.5); pointer-events: none;">
      <div class="model-video-overlay">
        FlashVSR 2x output (1280x768) from <code>flashvsr-v1.1-sparse-ratio-2.0</code>;
        low-resolution input (672x384) inset at bottom-left.

diff --git a/docs/source/models/hy_worldplay.rst b/docs/source/models/hy_worldplay.rst
@@ -28,17 +28,15 @@ real-time interactive image-to-video (I2V) world model with action + camera-traj
 reconstituted-context memory. FlashDreams ships a native port of the distilled WAN-5B variant (Wan 2.2
 TI2V-5B backbone, 4-step distilled Euler).
 
-.. raw:: html
+.. container:: model-video-card model-hero-media zoomable
 
-   <div class="model-video-card" style="width: 100%; margin: 10px auto 14px;">
-     <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-       <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/hy_worldplay/hy-worldplay-wan-i2v-5b-1.mp4" type="video/mp4">
-       Your browser does not support the video tag.
-     </video>
-   </div>
-   <p class="model-footnote">
-     Generated with FlashDreams' native HY-WorldPlay WAN-5B I2V pipeline.
-   </p>
+   .. image:: /_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-1.avif
+      :alt: HY-WorldPlay WAN-5B sample clip.
+      :class: model-video-player
+
+.. rst-class:: model-footnote
+
+Generated with FlashDreams' native HY-WorldPlay WAN-5B I2V pipeline.
 
 Installation
 ------------
@@ -90,37 +88,25 @@ Some generated samples from the above commands:
 
    <div class="model-video-grid">
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/hy_worldplay/hy-worldplay-wan-i2v-5b-2.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-2.avif" alt="HY-WorldPlay walking sample clip.">
        <div class="model-video-overlay">
          a person walking
        </div>
      </div>
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/hy_worldplay/hy-worldplay-wan-i2v-5b-4.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-4.avif" alt="HY-WorldPlay seaside village sample clip.">
        <div class="model-video-overlay">
          Walking through a seaside village
        </div>
      </div>
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/hy_worldplay/hy-worldplay-wan-i2v-5b-8.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-8.avif" alt="HY-WorldPlay snowy forest sample clip.">
        <div class="model-video-overlay">
          Walking through a snowy forest
        </div>
      </div>
      <div class="model-video-card">
-       <video class="model-video-player" autoplay muted loop playsinline preload="metadata">
-         <source src="https://research.nvidia.com/labs/sil/projects/flashdreams/assets/hy_worldplay/hy-worldplay-wan-i2v-5b-9.mp4" type="video/mp4">
-         Your browser does not support the video tag.
-       </video>
+       <img class="model-video-player" src="../_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-9.avif" alt="HY-WorldPlay castle sample clip.">
        <div class="model-video-overlay">
          Walking toward a castle
        </div>