Upload 2 files

README.md

@@ -89,7 +89,11 @@ Aug 2026. Free accounts can host up to 2 ZeroGPU Spaces.)
 ### Prompting tips (motion graphics)
 - Describe the scene **and** the motion: *"glossy chrome sphere rotating slowly,
   volumetric lighting, dark studio"*.
-- Keep clips short (~5s, 121 frames) — LTX-Video shines at short, single-shot clips.
+- Clip length: the model's max is **~10s** (257 frames). Drag the **Frames**
+  slider up for longer clips (more frames = more GPU quota per clip).
+- Need a *longer* video? Generate several short clips with matching prompts
+  (reuse the **seed** for visual consistency) and stitch them with any free
+  video editor — far more reliable than forcing one long generation.
 - More inference steps (40–50) = better quality but slower and more quota.
 - Reuse a **seed** to reproduce a video and iterate on it.
 

app.py

@@ -196,10 +196,10 @@ Your own video generation AI, running 100% in the cloud on Hugging Face GPUs
             with gr.Accordion("Settings", open=False):
                 num_frames = gr.Slider(
                     minimum=49,
-                    maximum=241,
+                    maximum=257,
                     value=121,
                     step=8,
-                    label="Frames (121 ≈ 5 seconds)",
+                    label="Frames (121 ≈ 5s, up to 257 ≈ 10s)",
                 )
                 resolution = gr.Dropdown(
                     list(RESOLUTIONS.keys()),