Upstream LTX2 Training (#1116)

Co-authored-by: RandNMR73 <notomatthew31@gmail.com>
Co-authored-by: JerryZhou54 <zhouw.jerry2017@outlook.com>
Co-authored-by: Davids048 <jundasu@ucsd.edu>
Co-authored-by: Peiyuan Zhang <a1286225768@slurm-h200-204-239.slurm-compute.tenant-slurm.svc.cluster.local>

examples/inference/basic/basic_ltx2.py

@@ -20,10 +20,10 @@ def main() -> None:
     # Uses FastVideo default sampling settings for LTX2 base.
     generator = VideoGenerator.from_pretrained(
         "Davids048/LTX2-Base-Diffusers",
-        num_gpus=8,
+        num_gpus=1,
     )
 
-    output_path = "outputs_video/ltx2_basic/output_ltx2_base_t2v_1088_1920_1.4.mp4"
+    output_path = "outputs_video/ltx2_basic/output_ltx2_base_t2v_1088_1920_1.1.mp4"
     generator.generate_video(
         prompt=PROMPT,
         output_path=output_path,
@@ -31,15 +31,9 @@ def main() -> None:
         num_frames=121,
         height=1088,
         width=1920,
-        # LTX2 uses these parameters for multi-modal CFG instead of guidance_scale
-        # ltx2_cfg_scale_video=3.0,
-        # ltx2_cfg_scale_audio=7.0,
-        # ltx2_modality_scale_video=3.0,
-        # ltx2_modality_scale_audio=3.0,
-        # ltx2_rescale_scale=0.7,
     )
     generator.shutdown()
 
 
 if __name__ == "__main__":
-    main()
+    main()