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 new file mode 100644 index 00000000..e2ed272f Binary files /dev/null and b/docs/source/_static/model_clips/causal_forcing/causal-forcing-wan2.1-i2v-1.3b-framewise.avif differ 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 new file mode 100644 index 00000000..eb50e054 Binary files /dev/null and b/docs/source/_static/model_clips/causal_forcing/causal-forcing-wan2.1-t2v-1.3b-framewise.avif differ 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 new file mode 100644 index 00000000..73eb5689 Binary files /dev/null and b/docs/source/_static/model_clips/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_1.avif differ 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 new file mode 100644 index 00000000..d1a38fa5 Binary files /dev/null and b/docs/source/_static/model_clips/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_2.avif differ diff --git a/docs/source/_static/model_clips/cosmos_predict2/cosmos-predict.avif b/docs/source/_static/model_clips/cosmos_predict2/cosmos-predict.avif new file mode 100644 index 00000000..f11ee4d1 Binary files /dev/null and b/docs/source/_static/model_clips/cosmos_predict2/cosmos-predict.avif differ 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 new file mode 100644 index 00000000..403b7b71 Binary files /dev/null and b/docs/source/_static/model_clips/cosmos_predict2/cosmos2-i2v-2b-720p.avif differ 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 new file mode 100644 index 00000000..867a0e54 Binary files /dev/null and b/docs/source/_static/model_clips/cosmos_predict2/cosmos2-t2v-2b-720p.avif differ diff --git a/docs/source/_static/model_clips/flashvsr/example1.avif b/docs/source/_static/model_clips/flashvsr/example1.avif new file mode 100644 index 00000000..09e4d5eb Binary files /dev/null and b/docs/source/_static/model_clips/flashvsr/example1.avif differ 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 new file mode 100644 index 00000000..a9f20543 Binary files /dev/null and b/docs/source/_static/model_clips/flashvsr/flashvsr-v1.1-sparse-ratio-2.0.avif differ 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 new file mode 100644 index 00000000..725b90de Binary files /dev/null and b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-hero.avif differ 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 new file mode 100644 index 00000000..725b90de Binary files /dev/null and b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-1.avif differ 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 new file mode 100644 index 00000000..002cb39f Binary files /dev/null and b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-2.avif differ 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 new file mode 100644 index 00000000..c2a8593d Binary files /dev/null and b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-4.avif differ 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 new file mode 100644 index 00000000..3fc30e06 Binary files /dev/null and b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-8.avif differ 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 new file mode 100644 index 00000000..9401bae8 Binary files /dev/null and b/docs/source/_static/model_clips/hy_worldplay/hy-worldplay-wan-i2v-5b-9.avif differ 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 new file mode 100644 index 00000000..001f7ab8 Binary files /dev/null and b/docs/source/_static/model_clips/lingbot_world/lingbot-world-fast-01.avif differ 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 new file mode 100644 index 00000000..c9fe440c Binary files /dev/null and b/docs/source/_static/model_clips/lingbot_world/lingbot-world-fast-02.avif differ 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 new file mode 100644 index 00000000..f8a5c65e Binary files /dev/null and b/docs/source/_static/model_clips/lingbot_world/lingbot-world-teaser.avif differ 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 new file mode 100644 index 00000000..df74cfed Binary files /dev/null and b/docs/source/_static/model_clips/lingbot_world/lingbot-world-traj-01.avif differ 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 new file mode 100644 index 00000000..a1db5220 Binary files /dev/null and b/docs/source/_static/model_clips/lingbot_world/lingbot-world-traj-02.avif differ 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 new file mode 100644 index 00000000..973f4f08 Binary files /dev/null and b/docs/source/_static/model_clips/lingbot_world/lingbot-world-webrtc-recording-0529.avif differ diff --git a/docs/source/_static/model_clips/omnidreams/omnidreams-sv-2steps-chunk2-loc6-lightvae-lighttae-239560dc-33d1-11ef-9720-00044bcbccac-pip.avif b/docs/source/_static/model_clips/omnidreams/omnidreams-sv-2steps-chunk2-loc6-lightvae-lighttae-239560dc-33d1-11ef-9720-00044bcbccac-pip.avif new file mode 100644 index 00000000..d19553a4 Binary files /dev/null and b/docs/source/_static/model_clips/omnidreams/omnidreams-sv-2steps-chunk2-loc6-lightvae-lighttae-239560dc-33d1-11ef-9720-00044bcbccac-pip.avif differ diff --git a/docs/source/_static/model_clips/omnidreams/omnidreams-sv-2steps-chunk2-loc6-lightvae-lighttae-24b84744-4156-11ef-b27d-00044bf655de-pip.avif b/docs/source/_static/model_clips/omnidreams/omnidreams-sv-2steps-chunk2-loc6-lightvae-lighttae-24b84744-4156-11ef-b27d-00044bf655de-pip.avif new file mode 100644 index 00000000..b87f20e8 Binary files /dev/null and b/docs/source/_static/model_clips/omnidreams/omnidreams-sv-2steps-chunk2-loc6-lightvae-lighttae-24b84744-4156-11ef-b27d-00044bf655de-pip.avif differ diff --git a/docs/source/_static/model_clips/omnidreams/omnidreams-teaser.avif b/docs/source/_static/model_clips/omnidreams/omnidreams-teaser.avif new file mode 100644 index 00000000..dbfb6c11 Binary files /dev/null and b/docs/source/_static/model_clips/omnidreams/omnidreams-teaser.avif differ 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 new file mode 100644 index 00000000..0826f95b Binary files /dev/null and b/docs/source/_static/model_clips/omnidreams/omnidreams-webrtc-recording-0529.avif differ 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 new file mode 100644 index 00000000..cbbe152e Binary files /dev/null and b/docs/source/_static/model_clips/self_forcing/self-forcing-wan2.1-t2v-1.3b-flash_1.avif differ 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 new file mode 100644 index 00000000..923872d8 Binary files /dev/null and b/docs/source/_static/model_clips/self_forcing/self-forcing-wan2.1-t2v-1.3b-flash_6.avif differ 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 new file mode 100644 index 00000000..d01340fe Binary files /dev/null and b/docs/source/_static/model_clips/wan21/wan21-i2v-14b-480p.avif differ 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 new file mode 100644 index 00000000..5ea2b55c Binary files /dev/null and b/docs/source/_static/model_clips/wan21/wan21-t2v-1.3b-480p.avif differ diff --git a/docs/source/models/causal_forcing.rst b/docs/source/models/causal_forcing.rst index df24d0a8..8e2255d7 100644 --- 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:
- + Causal-Forcing text-to-video sample clip.
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."
- + Causal-Forcing image-to-video sample clip.
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."
diff --git a/docs/source/models/causal_wan22.rst b/docs/source/models/causal_wan22.rst index a74df73d..5f339775 100644 --- 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:
- + Causal Wan 2.2 Tokyo street sample clip.
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."
- + Causal Wan 2.2 electronic guitar sample clip.
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."
diff --git a/docs/source/models/cosmos_predict2.rst b/docs/source/models/cosmos_predict2.rst index 35d10f4b..7d3c1a17 100644 --- 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 -
- -
-

- Teaser video source: - Cosmos-Predict2.5 project page. -

+ .. 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 `_. Requirements ------------ @@ -134,19 +132,13 @@ Some generated samples from the above commands:
- + Cosmos-Predict2.5 text-to-video sample clip.
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."
- + Cosmos-Predict2.5 image-to-video sample clip.
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."
diff --git a/docs/source/models/flashvsr.rst b/docs/source/models/flashvsr.rst index 840e0db3..8d80de43 100644 --- 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
- - + FlashVSR output sample clip. + FlashVSR low-resolution input inset.
FlashVSR 2x output (1280x768) from flashvsr-v1.1-sparse-ratio-2.0; low-resolution input (672x384) inset at bottom-left. diff --git a/docs/source/models/hy_worldplay.rst b/docs/source/models/hy_worldplay.rst index 2e9bd5c8..5a595746 100644 --- 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 -
- -
-

- Generated with FlashDreams' native HY-WorldPlay WAN-5B I2V pipeline. -

+ .. 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:
- + HY-WorldPlay walking sample clip.
a person walking
- + HY-WorldPlay seaside village sample clip.
Walking through a seaside village
- + HY-WorldPlay snowy forest sample clip.
Walking through a snowy forest
- + HY-WorldPlay castle sample clip.
Walking toward a castle
diff --git a/docs/source/models/index.rst b/docs/source/models/index.rst index 5fdca56a..642a44ce 100644 --- a/docs/source/models/index.rst +++ b/docs/source/models/index.rst @@ -62,11 +62,9 @@ uses, and the settings you can tune. :link: /models/omnidreams :link-type: doc - .. raw:: html - - + .. image:: /_static/model_clips/omnidreams/omnidreams-sv-2steps-chunk2-loc6-lightvae-lighttae-239560dc-33d1-11ef-9720-00044bcbccac-pip.avif + :alt: OmniDreams FlashDreams sample clip. + :class: fd-card-video Interactive world simulator for autonomous vehicles. @@ -75,11 +73,9 @@ uses, and the settings you can tune. :link: /models/self_forcing :link-type: doc - .. raw:: html - - + .. image:: /_static/model_clips/self_forcing/self-forcing-wan2.1-t2v-1.3b-flash_1.avif + :alt: Self-Forcing FlashDreams sample clip. + :class: fd-card-video Autoregressive text-to-video based on Wan 2.1. @@ -88,11 +84,9 @@ uses, and the settings you can tune. :link: /models/causal_forcing :link-type: doc - .. raw:: html - - + .. image:: /_static/model_clips/causal_forcing/causal-forcing-wan2.1-t2v-1.3b-framewise.avif + :alt: Causal-Forcing FlashDreams sample clip. + :class: fd-card-video Autoregressive text/image-to-video based on Wan 2.1. @@ -101,11 +95,9 @@ uses, and the settings you can tune. :link: /models/causal_wan22 :link-type: doc - .. raw:: html - - + .. image:: /_static/model_clips/causal_wan22/fastvideo-causal-wan2.2-t2v-14b_1.avif + :alt: Causal Wan 2.2 FlashDreams sample clip. + :class: fd-card-video Autoregressive text-to-video based on Wan 2.2 from FastVideo. @@ -117,12 +109,8 @@ uses, and the settings you can tune. .. raw:: html
- - + LingBot-World FlashDreams sample clip. + LingBot-World camera trajectory overlay.
Camera-controllable image-to-video world model. @@ -132,11 +120,9 @@ uses, and the settings you can tune. :link: /models/hy_worldplay :link-type: doc - .. raw:: html - - + .. image:: /_static/model_clips/hy_worldplay/hy-worldplay-hero.avif + :alt: HY-WorldPlay FlashDreams sample clip. + :class: fd-card-video Action- and camera-controllable image-to-video world model. @@ -164,11 +150,9 @@ uses, and the settings you can tune. :link: /models/wan21 :link-type: doc - .. raw:: html - - + .. image:: /_static/model_clips/wan21/wan21-t2v-1.3b-480p.avif + :alt: Wan 2.1 FlashDreams sample clip. + :class: fd-card-video Bidirectional video generation model that supports both text-to-video and image-to-video. @@ -178,11 +162,9 @@ uses, and the settings you can tune. :link: /models/cosmos_predict2 :link-type: doc - .. raw:: html - - + .. image:: /_static/model_clips/cosmos_predict2/cosmos2-t2v-2b-720p.avif + :alt: Cosmos-Predict2.5 FlashDreams sample clip. + :class: fd-card-video Bidirectional Cosmos-Predict2 reference implementations (T2V / I2V, 2B). @@ -210,11 +192,9 @@ uses, and the settings you can tune. :link: /models/flashvsr :link-type: doc - .. raw:: html - - + .. image:: /_static/model_clips/flashvsr/flashvsr-v1.1-sparse-ratio-2.0.avif + :alt: FlashVSR FlashDreams sample clip. + :class: fd-card-video Streaming video super-resolution. diff --git a/docs/source/models/lingbot_world.rst b/docs/source/models/lingbot_world.rst index 34e7fe7a..a02fc872 100644 --- a/docs/source/models/lingbot_world.rst +++ b/docs/source/models/lingbot_world.rst @@ -33,18 +33,16 @@ Introduced by `Robbyant `_, LingBot-World is a `LingBot-World v1 `_ and the newer 14B causal-fast `LingBot-World v2 `_ checkpoints. -.. raw:: html +.. container:: model-video-card model-hero-media zoomable -
- -
-

- Teaser video source: - LingBot-World project page. -

+ .. image:: /_static/model_clips/lingbot_world/lingbot-world-teaser.avif + :alt: LingBot-World teaser clip. + :class: model-video-player + +.. rst-class:: model-footnote + +Teaser video source: +`LingBot-World project page `_. Requirements ------------ @@ -191,27 +189,15 @@ Some generated samples from the above commands:
- - + LingBot-World sample clip for example index 01. + LingBot-World camera trajectory overlay for example index 01.
example_idx: 01
- - + LingBot-World sample clip for example index 02. + LingBot-World camera trajectory overlay for example index 02.
example_idx: 02
@@ -261,14 +247,11 @@ first launch, much faster afterwards. When ready the server prints When successfully connected, the browser-based UI looks like this: -.. raw:: html +.. container:: model-video-card model-hero-media zoomable -
- -
+ .. image:: /_static/model_clips/lingbot_world/lingbot-world-webrtc-recording-0529.avif + :alt: LingBot-World browser UI recording. + :class: model-video-player Profiling benchmark ------------------- diff --git a/docs/source/models/omnidreams.rst b/docs/source/models/omnidreams.rst index 60db7e64..25dce9aa 100644 --- a/docs/source/models/omnidreams.rst +++ b/docs/source/models/omnidreams.rst @@ -42,18 +42,16 @@ OmniDreams is a HDMap-conditioned world model for single-view and multi-view driving generation, with presets that balance visual fidelity and runtime throughput. -.. raw:: html +.. container:: model-video-card model-hero-media zoomable -
- -
-

- Teaser video source: - OmniDreams project page. -

+ .. image:: /_static/model_clips/omnidreams/omnidreams-teaser.avif + :alt: OmniDreams teaser clip. + :class: model-video-player + +.. rst-class:: model-footnote + +Teaser video source: +`OmniDreams project page `_. Requirements ------------ @@ -125,20 +123,14 @@ Some generated samples from the above commands:
- + OmniDreams sample clip for example data UUID 239560dc.
example_data_uuid: "239560dc-33d1-11ef-9720-00044bcbccac"
- + OmniDreams sample clip for example data UUID 24b84744.
example_data_uuid: "24b84744-4156-11ef-b27d-00044bf655de"
@@ -361,14 +353,11 @@ Here, ```` is the server IP address you are connecting to Once successfully connected, the browser-based UI looks like this: -.. raw:: html +.. container:: model-video-card model-hero-media zoomable -
- -
+ .. image:: /_static/model_clips/omnidreams/omnidreams-webrtc-recording-0529.avif + :alt: OmniDreams browser UI recording. + :class: model-video-player .. note:: diff --git a/docs/source/models/self_forcing.rst b/docs/source/models/self_forcing.rst index 2a695580..06d3171d 100644 --- a/docs/source/models/self_forcing.rst +++ b/docs/source/models/self_forcing.rst @@ -159,20 +159,14 @@ Some generated samples from the above commands:
- + Self-Forcing teacup sample clip.
A close-up shot of a ceramic teacup slowly pouring water into a glass mug. The water flows smoothly from the spout of the teacup into the mug, creating gentle ripples as it fills up. Both cups have detailed textures, with the teacup having a matte finish and the glass mug showcasing clear transparency. The background is a blurred kitchen countertop, adding context without distracting from the central action. The pouring motion is fluid and natural, emphasizing the interaction between the two cups.
- + Self-Forcing tsunami sample clip.
A dramatic and dynamic scene in the style of a disaster movie, depicting a powerful tsunami rushing through a narrow alley in Bulgaria. The water is turbulent and chaotic, with waves crashing violently against the walls and buildings on either side. The alley is lined with old, weathered houses, their facades partially submerged and splintered. The camera angle is low, capturing the full force of the tsunami as it surges forward, creating a sense of urgency and danger. People can be seen running frantically, adding to the chaos. The background features a distant horizon, hinting at the larger scale of the tsunami. A dynamic, sweeping shot from a low-angle perspective, emphasizing the movement and intensity of the event.
diff --git a/docs/source/models/wan21.rst b/docs/source/models/wan21.rst index 7d3d3f57..bebfc4b8 100644 --- a/docs/source/models/wan21.rst +++ b/docs/source/models/wan21.rst @@ -113,19 +113,13 @@ Some generated samples from the above commands:
- + Wan 2.1 text-to-video sample clip.
prompt: "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
- + Wan 2.1 image-to-video sample clip.
prompt: "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."