update

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

docs/inference/inference_quick_start.md

@@ -106,6 +106,8 @@ If you encounter CUDA out of memory errors:
 - Enable memory optimization with `enable_model_cpu_offload`
 - Try a smaller model or use distilled versions
 - Use `num_gpus` > 1 if multiple GPUs are available
+- Try enabling FSDP inference with `use_fsdp_inference=True` (may slow down generation)
+- Try enabling DiT layerwise offload with `dit_layerwise_offload=True` (now only a few models support this, but may introduce less overhead than FSDP)
 
 ### Slow Generation
 

docs/utilities/lora.md

@@ -0,0 +1,71 @@
+# LoRA Extraction and Merging
+
+Tools for extracting and merging LoRA adapters for FastVideo models.
+
+## Extract LoRA Adapter
+
+```bash
+python scripts/lora_extraction/extract_lora.py \
+  --base Wan-AI/Wan2.2-TI2V-5B-Diffusers \
+  --ft FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers \
+  --out adapter_r32.safetensors \
+  --rank 32
+```
+
+**Options:**
+
+- `--base`: Base model (HuggingFace ID or local path)
+- `--ft`: Fine-tuned model (HuggingFace ID or local path)
+- `--out`: Output adapter file
+- `--rank`: LoRA rank (16, 32, 64, 128)
+- `--full-rank`: Extract full-rank adapter (optional)
+
+## Merge Adapter
+
+```bash
+python scripts/lora_extraction/merge_lora.py \
+  --base Wan-AI/Wan2.2-TI2V-5B-Diffusers \
+  --adapter adapter_r32.safetensors \
+  --ft FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers \
+  --output merged_model
+```
+
+**Options:**
+
+- `--base`: Base model (HuggingFace ID or local path)
+- `--adapter`: LoRA adapter file (.safetensors)
+- `--ft`: Fine-tuned model (for configuration)
+- `--output`: Output directory
+
+## Validate Quality (Optional)
+
+```bash
+python scripts/lora_extraction/lora_inference_comparison.py \
+  --base merged_model \
+  --ft FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers \
+  --adapter NONE \
+  --output-dir results \
+  --prompt "A cat sitting on a windowsill" \
+  --seed 42 \
+  --height 480 \
+  --width 480 \
+  --num-frames 49 \
+  --num-inference-steps 32 \
+  --compute-ssim \
+  --compute-lpips
+```
+
+**Options:**
+
+- `--base`: Merged model or base model path
+- `--ft`: Fine-tuned model (reference)
+- `--adapter`: Path to adapter or NONE
+- `--output-dir`: Output directory
+- `--prompt`: Text prompt (default: "A cat sitting on a windowsill")
+- `--seed`: Random seed (default: 42)
+- `--height`: Video height (default: 480)
+- `--width`: Video width (default: 832)
+- `--num-frames`: Number of frames (default: 49)
+- `--num-inference-steps`: Inference steps (default: 32)
+- `--compute-ssim`: Compute SSIM metric
+- `--compute-lpips`: Compute LPIPS metric

examples/inference/basic/basic.py

@@ -12,7 +12,7 @@ def main():
         "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         dit_cpu_offload=False,
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,

examples/inference/basic/basic_dmd.py

@@ -14,7 +14,7 @@ def main():
         model_name,
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         # Adjust these offload parameters if you have < 32GB of VRAM
         text_encoder_cpu_offload=True,
         pin_cpu_memory=True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"

examples/inference/basic/basic_hy15.py

@@ -12,7 +12,7 @@ def main():
         "hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v",
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         dit_cpu_offload=True,
         vae_cpu_offload=True,
         text_encoder_cpu_offload=True,

examples/inference/basic/basic_longcat_i2v.py

@@ -0,0 +1,210 @@
+"""
+LongCat Image-to-Video (I2V) Example Script
+
+This script demonstrates LongCat I2V inference using the FastVideo Python API.
+LongCat I2V takes an input image and generates a video from it.
+
+It runs both basic generation (50 steps) and distill+refine generation
+(16 steps distill + 50 steps refinement to 720p with BSA).
+
+Usage:
+    python examples/inference/basic/basic_longcat_i2v.py
+
+Note:
+    Refinement uses 768x768 dimensions where latent (48x48) is divisible by 8,
+    compatible with BSA chunks [4, 4, 8].
+"""
+
+import glob
+import os
+
+from fastvideo import VideoGenerator
+
+# Common prompts and settings matching the shell script examples
+PROMPT = (
+    "A woman sits at a wooden table by the window in a cozy café. She reaches out "
+    "with her right hand, picks up the white coffee cup from the saucer, and gently "
+    "brings it to her lips to take a sip. After drinking, she places the cup back on "
+    "the table and looks out the window, enjoying the peaceful atmosphere."
+)
+
+NEGATIVE_PROMPT = (
+    "Bright tones, overexposed, static, blurred details, subtitles, style, works, "
+    "paintings, images, static, overall gray, worst quality, low quality, JPEG compression "
+    "residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, "
+    "deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, "
+    "three legs, many people in the background, walking backwards"
+)
+
+# Input image path
+IMAGE_PATH = "assets/girl.png"
+
+SEED = 42
+
+
+def basic_generation():
+    """
+    Run basic LongCat I2V generation (50 steps at 480p).
+    
+    This uses the full 50-step denoising process for highest quality.
+    """
+    print("=" * 60)
+    print("LongCat I2V: Basic Generation (50 steps, 480p)")
+    print("=" * 60)
+    
+    generator = VideoGenerator.from_pretrained(
+        "FastVideo/LongCat-Video-I2V-Diffusers",
+        num_gpus=1,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
+        dit_cpu_offload=False,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=False,
+        enable_bsa=False,
+    )
+    
+    output_path = "outputs_video/longcat_i2v_basic"
+    
+    generator.generate_video(
+        prompt=PROMPT,
+        negative_prompt=NEGATIVE_PROMPT,
+        image_path=IMAGE_PATH,
+        output_path=output_path,
+        save_video=True,
+        height=480,
+        width=480,  # Square
+        num_frames=93,
+        num_inference_steps=50,
+        fps=15,
+        guidance_scale=4.0,
+        seed=SEED,
+    )
+    
+    print(f"\nBasic generation complete! Video saved to: {output_path}")
+    generator.shutdown()
+
+
+def distill_refine_generation():
+    """
+    Run LongCat I2V with distill+refine pipeline (16 steps + refinement to 768p).
+    
+    This uses the distilled LoRA for fast 480p generation (16 steps),
+    then refines to 768p using the refinement LoRA with BSA enabled.
+    """
+    print("\n" + "=" * 60)
+    print("LongCat I2V: Distill + Refine Pipeline")
+    print("=" * 60)
+    
+    # Stage 1: Distilled generation (16 steps at 480p)
+    print("\n[Stage 1] Distilled generation (16 steps, 480p)")
+    print("-" * 40)
+    
+    generator = VideoGenerator.from_pretrained(
+        "FastVideo/LongCat-Video-I2V-Diffusers",
+        num_gpus=1,
+        use_fsdp_inference=True,
+        dit_cpu_offload=False,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=False,
+        enable_bsa=False,
+        lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
+        lora_nickname="distilled",
+    )
+    
+    distill_output_path = "outputs_video/longcat_i2v_distill"
+    
+    generator.generate_video(
+        prompt=PROMPT,
+        negative_prompt=NEGATIVE_PROMPT,
+        image_path=IMAGE_PATH,
+        output_path=distill_output_path,
+        save_video=True,
+        height=480,
+        width=480,  # Square
+        num_frames=93,
+        num_inference_steps=16,
+        fps=15,
+        guidance_scale=1.0,
+        seed=SEED,
+    )
+    
+    print(f"Distilled generation complete! Video saved to: {distill_output_path}")
+    generator.shutdown()
+    
+    # Stage 2: Refinement (480p -> 768p)
+    print("\n[Stage 2] Refinement (480p -> 768p with BSA)")
+    print("-" * 40)
+    
+    # Find the actual saved video file from stage 1
+    video_files = glob.glob(os.path.join(distill_output_path, "*.mp4"))
+    if not video_files:
+        raise FileNotFoundError(f"No video file found in {distill_output_path}")
+    # Use the most recently created video file
+    distill_video_path = max(video_files, key=os.path.getmtime)
+    print(f"Using stage 1 video: {distill_video_path}")
+    
+    # Create a new generator with refinement LoRA and BSA enabled
+    # Note: Refinement uses the T2V model (not I2V) since it's upscaling the generated video
+    # For BSA [4, 4, 8]: latent must be divisible by 8
+    # 768x768: latent 48x48, 48%8=0 ✓
+    refine_generator = VideoGenerator.from_pretrained(
+        "FastVideo/LongCat-Video-T2V-Diffusers",
+        num_gpus=1,
+        use_fsdp_inference=True,
+        dit_cpu_offload=True,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=False,
+        enable_bsa=True,
+        bsa_sparsity=0.875,
+        bsa_chunk_q=[4, 4, 4],
+        bsa_chunk_k=[4, 4, 4],
+        lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
+        lora_nickname="refinement",
+    )
+    
+    refine_output_path = "outputs_video/longcat_i2v_refine_720p"
+    
+    refine_generator.generate_video(
+        prompt=PROMPT,
+        negative_prompt=NEGATIVE_PROMPT,
+        output_path=refine_output_path,
+        save_video=True,
+        refine_from=distill_video_path,
+        t_thresh=0.5,
+        spatial_refine_only=False,
+        num_cond_frames=0,
+        height=720,
+        width=720,
+        num_inference_steps=50,
+        fps=30,
+        guidance_scale=1.0,
+        seed=SEED,
+    )
+    
+    print(f"Refinement complete! Video saved to: {refine_output_path}")
+    refine_generator.shutdown()
+
+
+def main():
+    """Run both basic and distill+refine generation pipelines."""
+    print("\n" + "=" * 60)
+    print("LongCat Image-to-Video Example")
+    print("=" * 60 + "\n")
+    
+    # Run basic generation
+    basic_generation()
+    
+    # Run distill+refine pipeline
+    distill_refine_generation()
+    
+    print("\n" + "=" * 60)
+    print("All generations complete!")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()
+
+

examples/inference/basic/basic_longcat_t2v.py

@@ -0,0 +1,198 @@
+"""
+LongCat Text-to-Video (T2V) Example Script
+
+This script demonstrates LongCat T2V inference using the FastVideo Python API.
+It runs both basic generation (50 steps) and distill+refine generation
+(16 steps distill + 50 steps refinement to 720p).
+
+Usage:
+    python examples/inference/basic/basic_longcat_t2v.py
+"""
+
+import glob
+import os
+
+from fastvideo import VideoGenerator
+
+# Common prompts and settings matching the shell script examples
+PROMPT = (
+    "In a realistic photography style, a white boy around seven or eight years old "
+    "sits on a park bench, wearing a light blue T-shirt, denim shorts, and white sneakers. "
+    "He holds an ice cream cone with vanilla and chocolate flavors, and beside him is a "
+    "medium-sized golden Labrador. Smiling, the boy offers the ice cream to the dog, "
+    "who eagerly licks it with its tongue. The sun is shining brightly, and the background "
+    "features a green lawn and several tall trees, creating a warm and loving scene."
+)
+
+NEGATIVE_PROMPT = (
+    "Bright tones, overexposed, static, blurred details, subtitles, style, works, "
+    "paintings, images, static, overall gray, worst quality, low quality, JPEG compression "
+    "residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, "
+    "deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, "
+    "three legs, many people in the background, walking backwards"
+)
+
+SEED = 42
+
+
+def basic_generation():
+    """
+    Run basic LongCat T2V generation (50 steps at 480p).
+    
+    This uses the full 50-step denoising process for highest quality.
+    """
+    print("=" * 60)
+    print("LongCat T2V: Basic Generation (50 steps, 480p)")
+    print("=" * 60)
+    
+    generator = VideoGenerator.from_pretrained(
+        "FastVideo/LongCat-Video-T2V-Diffusers",
+        num_gpus=1,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
+        dit_cpu_offload=False,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=False,
+        enable_bsa=False,
+    )
+    
+    output_path = "outputs_video/longcat_t2v_basic"
+    
+    generator.generate_video(
+        prompt=PROMPT,
+        negative_prompt=NEGATIVE_PROMPT,
+        output_path=output_path,
+        save_video=True,
+        height=480,
+        width=832,
+        num_frames=93,
+        num_inference_steps=50,
+        fps=15,
+        guidance_scale=4.0,
+        seed=SEED,
+    )
+    
+    print(f"\nBasic generation complete! Video saved to: {output_path}")
+    generator.shutdown()
+
+
+def distill_refine_generation():
+    """
+    Run LongCat T2V with distill+refine pipeline (16 steps + refinement to 720p).
+    
+    This uses the distilled LoRA for fast 480p generation (16 steps),
+    then refines to 720p using the refinement LoRA with BSA enabled.
+    """
+    print("\n" + "=" * 60)
+    print("LongCat T2V: Distill + Refine Pipeline")
+    print("=" * 60)
+    
+    # Stage 1: Distilled generation (16 steps at 480p)
+    print("\n[Stage 1] Distilled generation (16 steps, 480p)")
+    print("-" * 40)
+    
+    generator = VideoGenerator.from_pretrained(
+        "FastVideo/LongCat-Video-T2V-Diffusers",
+        num_gpus=1,
+        use_fsdp_inference=True,
+        dit_cpu_offload=False,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=False,
+        enable_bsa=False,
+        lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
+        lora_nickname="distilled",
+    )
+    
+    distill_output_path = "outputs_video/longcat_t2v_distill"
+    
+    generator.generate_video(
+        prompt=PROMPT,
+        negative_prompt=NEGATIVE_PROMPT,
+        output_path=distill_output_path,
+        save_video=True,
+        height=480,
+        width=832,
+        num_frames=93,
+        num_inference_steps=16,
+        fps=15,
+        guidance_scale=1.0,
+        seed=SEED,
+    )
+    
+    print(f"Distilled generation complete! Video saved to: {distill_output_path}")
+    generator.shutdown()
+    
+    # Stage 2: Refinement (480p -> 720p)
+    print("\n[Stage 2] Refinement (480p -> 720p with BSA)")
+    print("-" * 40)
+    
+    # Find the actual saved video file from stage 1
+    video_files = glob.glob(os.path.join(distill_output_path, "*.mp4"))
+    if not video_files:
+        raise FileNotFoundError(f"No video file found in {distill_output_path}")
+    # Use the most recently created video file
+    distill_video_path = max(video_files, key=os.path.getmtime)
+    print(f"Using stage 1 video: {distill_video_path}")
+    
+    # Create a new generator with refinement LoRA and BSA enabled
+    refine_generator = VideoGenerator.from_pretrained(
+        "FastVideo/LongCat-Video-T2V-Diffusers",
+        num_gpus=1,
+        use_fsdp_inference=True,
+        dit_cpu_offload=True,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=False,
+        enable_bsa=True,
+        bsa_sparsity=0.875,
+        bsa_chunk_q=[4, 4, 8],
+        bsa_chunk_k=[4, 4, 8],
+        lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
+        lora_nickname="refinement",
+    )
+    
+    refine_output_path = "outputs_video/longcat_t2v_refine_720p"
+    
+    refine_generator.generate_video(
+        prompt=PROMPT,
+        negative_prompt=NEGATIVE_PROMPT,
+        output_path=refine_output_path,
+        save_video=True,
+        refine_from=distill_video_path,
+        t_thresh=0.5,
+        spatial_refine_only=False,
+        num_cond_frames=0,
+        height=720,
+        width=1280,
+        num_inference_steps=50,
+        fps=30,
+        guidance_scale=1.0,
+        seed=SEED,
+    )
+    
+    print(f"Refinement complete! Video saved to: {refine_output_path}")
+    refine_generator.shutdown()
+
+
+def main():
+    """Run both basic and distill+refine generation pipelines."""
+    print("\n" + "=" * 60)
+    print("LongCat Text-to-Video Example")
+    print("=" * 60 + "\n")
+    
+    # Run basic generation
+    basic_generation()
+    
+    # Run distill+refine pipeline
+    distill_refine_generation()
+    
+    print("\n" + "=" * 60)
+    print("All generations complete!")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()
+
+

examples/inference/basic/basic_longcat_vc.py

@@ -0,0 +1,228 @@
+"""
+LongCat Video Continuation (VC) Example Script
+
+This script demonstrates LongCat VC inference using the FastVideo Python API.
+LongCat VC takes an input video and generates a continuation of it.
+
+It runs both basic generation (50 steps) and distill+refine generation
+(16 steps distill + 50 steps refinement to 720p).
+
+Usage:
+    python examples/inference/basic/basic_longcat_vc.py
+
+Prerequisites:
+    - Ensure the input video exists at assets/motorcycle.mp4
+      (or provide your own video)
+"""
+
+import glob
+import os
+
+from fastvideo import VideoGenerator
+
+# Common prompts and settings matching the shell script examples
+PROMPT = (
+    "A person rides a motorcycle along a long, straight road that stretches between "
+    "a body of water and a forested hillside. The rider steadily accelerates, keeping "
+    "the motorcycle centered between the guardrails, while the scenery passes by on "
+    "both sides. The video captures the journey from the rider's perspective, emphasizing "
+    "the sense of motion and adventure."
+)
+
+NEGATIVE_PROMPT = (
+    "Bright tones, overexposed, static, blurred details, subtitles, style, works, "
+    "paintings, images, static, overall gray, worst quality, low quality, JPEG compression "
+    "residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, "
+    "deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, "
+    "three legs, many people in the background, walking backwards"
+)
+
+# Input video path
+VIDEO_PATH = "assets/motorcycle.mp4"
+
+# Number of conditioning frames from the input video
+NUM_COND_FRAMES = 13
+
+SEED = 42
+
+
+def basic_generation():
+    """
+    Run basic LongCat VC generation (50 steps at 480p).
+    
+    This uses the full 50-step denoising process for highest quality.
+    """
+    print("=" * 60)
+    print("LongCat VC: Basic Generation (50 steps, 480p)")
+    print("=" * 60)
+    
+    # Check if video exists
+    if not os.path.exists(VIDEO_PATH):
+        raise FileNotFoundError(
+            f"Video not found at {VIDEO_PATH}. "
+            "Please provide a valid video path."
+        )
+    
+    generator = VideoGenerator.from_pretrained(
+        "FastVideo/LongCat-Video-VC-Diffusers",
+        num_gpus=1,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
+        dit_cpu_offload=False,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=False,
+        enable_bsa=False,
+    )
+    
+    output_path = "outputs_video/longcat_vc_basic"
+    
+    generator.generate_video(
+        prompt=PROMPT,
+        negative_prompt=NEGATIVE_PROMPT,
+        video_path=VIDEO_PATH,
+        num_cond_frames=NUM_COND_FRAMES,
+        output_path=output_path,
+        save_video=True,
+        height=480,
+        width=832,
+        num_frames=93,
+        num_inference_steps=50,
+        fps=15,
+        guidance_scale=4.0,
+        seed=SEED,
+    )
+    
+    print(f"\nBasic generation complete! Video saved to: {output_path}")
+    generator.shutdown()
+
+
+def distill_refine_generation():
+    """
+    Run LongCat VC with distill+refine pipeline (16 steps + refinement to 720p).
+    
+    This uses the distilled LoRA for fast 480p generation (16 steps),
+    then refines to 720p using the refinement LoRA with BSA enabled.
+    """
+    print("\n" + "=" * 60)
+    print("LongCat VC: Distill + Refine Pipeline")
+    print("=" * 60)
+    
+    # Check if video exists
+    if not os.path.exists(VIDEO_PATH):
+        raise FileNotFoundError(
+            f"Video not found at {VIDEO_PATH}. "
+            "Please provide a valid video path."
+        )
+    
+    # Stage 1: Distilled generation (16 steps at 480p)
+    print("\n[Stage 1] Distilled generation (16 steps, 480p)")
+    print("-" * 40)
+    
+    generator = VideoGenerator.from_pretrained(
+        "FastVideo/LongCat-Video-VC-Diffusers",
+        num_gpus=1,
+        use_fsdp_inference=True,
+        dit_cpu_offload=False,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=False,
+        enable_bsa=False,
+        lora_path="FastVideo/LongCat-Video-T2V-Distilled-LoRA",
+        lora_nickname="distilled",
+    )
+    
+    distill_output_path = "outputs_video/longcat_vc_distill"
+    
+    generator.generate_video(
+        prompt=PROMPT,
+        negative_prompt=NEGATIVE_PROMPT,
+        video_path=VIDEO_PATH,
+        num_cond_frames=NUM_COND_FRAMES,
+        output_path=distill_output_path,
+        save_video=True,
+        height=480,
+        width=832,
+        num_frames=93,
+        num_inference_steps=16,
+        fps=15,
+        guidance_scale=1.0,
+        seed=SEED,
+    )
+    
+    print(f"Distilled generation complete! Video saved to: {distill_output_path}")
+    generator.shutdown()
+    
+    # Stage 2: Refinement (480p -> 720p)
+    print("\n[Stage 2] Refinement (480p -> 720p with BSA)")
+    print("-" * 40)
+    
+    # Find the actual saved video file from stage 1
+    video_files = glob.glob(os.path.join(distill_output_path, "*.mp4"))
+    if not video_files:
+        raise FileNotFoundError(f"No video file found in {distill_output_path}")
+    # Use the most recently created video file
+    distill_video_path = max(video_files, key=os.path.getmtime)
+    print(f"Using stage 1 video: {distill_video_path}")
+    
+    # Create a new generator with refinement LoRA and BSA enabled
+    # Note: Refinement uses the T2V model (not VC) since it's upscaling the generated video
+    refine_generator = VideoGenerator.from_pretrained(
+        "FastVideo/LongCat-Video-T2V-Diffusers",
+        num_gpus=1,
+        use_fsdp_inference=True,
+        dit_cpu_offload=True,
+        vae_cpu_offload=True,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=False,
+        enable_bsa=True,
+        bsa_sparsity=0.875,
+        bsa_chunk_q=[4, 4, 8],
+        bsa_chunk_k=[4, 4, 8],
+        lora_path="FastVideo/LongCat-Video-T2V-Refinement-LoRA",
+        lora_nickname="refinement",
+    )
+    
+    refine_output_path = "outputs_video/longcat_vc_refine_720p"
+    
+    refine_generator.generate_video(
+        prompt=PROMPT,
+        negative_prompt=NEGATIVE_PROMPT,
+        output_path=refine_output_path,
+        save_video=True,
+        refine_from=distill_video_path,
+        t_thresh=0.5,
+        spatial_refine_only=False,
+        num_cond_frames=0,  # For refinement, no conditioning frames
+        height=720,
+        width=1280,
+        num_inference_steps=50,
+        fps=30,
+        guidance_scale=1.0,
+        seed=SEED,
+    )
+    
+    print(f"Refinement complete! Video saved to: {refine_output_path}")
+    refine_generator.shutdown()
+
+
+def main():
+    """Run both basic and distill+refine generation pipelines."""
+    print("\n" + "=" * 60)
+    print("LongCat Video Continuation Example")
+    print("=" * 60 + "\n")
+    
+    # Run basic generation
+    basic_generation()
+    
+    # Run distill+refine pipeline
+    distill_refine_generation()
+    
+    print("\n" + "=" * 60)
+    print("All generations complete!")
+    print("=" * 60)
+
+
+if __name__ == "__main__":
+    main()
+
+

examples/inference/basic/basic_matrixgame.py

@@ -43,7 +43,7 @@ def main():
         config["model_path"],
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         dit_cpu_offload=True, # DiT need to be offloaded for MoE
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,

examples/inference/basic/basic_matrixgame_streaming.py

@@ -46,7 +46,7 @@ async def main():
         config["model_path"],
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         dit_cpu_offload=True, # DiT need to be offloaded for MoE
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,

examples/inference/basic/basic_self_forcing_causal.py

@@ -13,7 +13,7 @@ def main():
         model_name,
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         text_encoder_cpu_offload=False,
         dit_cpu_offload=False,
     )

examples/inference/basic/basic_self_forcing_causal_wan2_2_i2v.py

@@ -14,7 +14,7 @@ def main():
         "FastVideo/SFWan2.2-I2V-A14B-Preview-Diffusers",
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         dit_cpu_offload=True, # DiT need to be offloaded for MoE
         dit_precision="fp32",
         vae_cpu_offload=False,

examples/inference/basic/basic_self_forcing_causal_wan2_2_t2v.py

@@ -14,7 +14,7 @@ def main():
         "rand0nmr/SFWan2.2-T2V-A14B-Diffusers",
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         dit_cpu_offload=True, # DiT need to be offloaded for MoE
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,

examples/inference/basic/basic_turbodiffusion.py

@@ -15,15 +15,14 @@ def main() -> None:
         "loayrashid/TurboWan2.1-T2V-1.3B-Diffusers",
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        # TurboDiffusion uses a custom pipeline with RCM scheduler
-        override_pipeline_cls_name="TurboDiffusionPipeline",
+        use_fsdp_inference=False, # set to True if GPU is out of memory
 
         # set to false if using RTX 4090 
         # pin_cpu_memory=False,
     )
 
     # Generate videos with the same simple API, regardless of GPU count
-    # TurboDiffusion uses guidance_scale=1.0 (no CFG) and only 4 steps
+    # TurboDiffusion defaults: guidance_scale=1.0 and num_inference_steps=4 (from config)
     prompt = (
         "A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "
         "wide with interest. The playful yet serene atmosphere is complemented by soft "
@@ -33,9 +32,7 @@ def main() -> None:
         prompt,
         output_path=OUTPUT_PATH,
         save_video=True,
-        num_inference_steps=4,
         seed=42,
-        guidance_scale=1.0,
     )
 
     # Generate another video with a different prompt, without reloading the model!
@@ -50,9 +47,7 @@ def main() -> None:
         prompt2,
         output_path=OUTPUT_PATH,
         save_video=True,
-        num_inference_steps=4,
         seed=42,
-        guidance_scale=1.0,
     )
 
 

examples/inference/basic/basic_turbodiffusion_14b.py

@@ -15,8 +15,6 @@ def main() -> None:
         "loayrashid/TurboWan2.1-T2V-14B-Diffusers",
         # 14B model needs more GPUs
         num_gpus=2,
-        # TurboDiffusion uses a custom pipeline with RCM scheduler
-        override_pipeline_cls_name="TurboDiffusionPipeline",
     )
 
     prompt = (
@@ -28,9 +26,7 @@ def main() -> None:
         prompt,
         output_path=OUTPUT_PATH,
         save_video=True,
-        num_inference_steps=4,
         seed=42,
-        guidance_scale=1.0,
     )
 
     # Generate another video with a different prompt, without reloading the model!
@@ -45,9 +41,7 @@ def main() -> None:
         prompt2,
         output_path=OUTPUT_PATH,
         save_video=True,
-        num_inference_steps=4,
         seed=42,
-        guidance_scale=1.0,
     )
 
 

examples/inference/basic/basic_turbodiffusion_i2v.py

@@ -12,11 +12,9 @@ OUTPUT_PATH = "video_samples_turbodiffusion_i2v"
 
 def main() -> None:
     # TurboDiffusion I2V: 1-4 step image-to-video generation
-    # Uses RCM scheduler with sigma_max=200 for I2V
     generator = VideoGenerator.from_pretrained(
         MODEL_PATH,
         num_gpus=2,
-        override_pipeline_cls_name="TurboDiffusionI2VPipeline",
     )
 
     # Example prompt and image for I2V
@@ -31,9 +29,7 @@ def main() -> None:
         image_path=image_path,
         output_path=OUTPUT_PATH,
         save_video=True,
-        num_inference_steps=4,
         seed=42,
-        guidance_scale=1.0,
     )
 
 

examples/inference/basic/basic_wan2_2.py

@@ -12,7 +12,7 @@ def main():
         "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory 
         dit_cpu_offload=True, # DiT need to be offloaded for MoE
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,

examples/inference/basic/basic_wan2_2_Fun.py

@@ -14,7 +14,7 @@ def main():
         # "alibaba-pai/Wan2.2-Fun-A14B-Control",
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         dit_cpu_offload=True, # DiT need to be offloaded for MoE
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,

examples/inference/basic/basic_wan2_2_i2v.py

@@ -12,7 +12,7 @@ def main():
         "Wan-AI/Wan2.2-I2V-A14B-Diffusers",
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         dit_cpu_offload=True, # DiT need to be offloaded for MoE
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,

examples/inference/basic/basic_wan2_2_ti2v.py

@@ -11,7 +11,7 @@ def main():
         model_name,
         # FastVideo will automatically handle distributed setup
         num_gpus=1,
-        use_fsdp_inference=True,
+        use_fsdp_inference=False, # set to True if GPU is out of memory
         dit_cpu_offload=True,
         vae_cpu_offload=False,
         text_encoder_cpu_offload=True,

fastvideo/configs/pipelines/registry.py

@@ -10,6 +10,9 @@ from fastvideo.configs.pipelines.hunyuan import FastHunyuanConfig, HunyuanConfig
 from fastvideo.configs.pipelines.hunyuan15 import Hunyuan15T2V480PConfig, Hunyuan15T2V720PConfig
 from fastvideo.configs.pipelines.stepvideo import StepVideoT2VConfig
 from fastvideo.configs.pipelines.longcat import LongCatT2V480PConfig
+from fastvideo.configs.pipelines.turbodiffusion import (
+    TurboDiffusionT2V_1_3B_Config, TurboDiffusionT2V_14B_Config,
+    TurboDiffusionI2V_A14B_Config)
 
 # isort: off
 from fastvideo.configs.pipelines.wan import (
@@ -59,6 +62,10 @@ PIPE_NAME_TO_CONFIG: dict[str, type[PipelineConfig]] = {
     "FastVideo/LongCat-Video-T2V-Diffusers": LongCatT2V480PConfig,
     "FastVideo/LongCat-Video-I2V-Diffusers": LongCatT2V480PConfig,
     "FastVideo/LongCat-Video-VC-Diffusers": LongCatT2V480PConfig,
+    # TurboDiffusion models
+    "loayrashid/TurboWan2.1-T2V-1.3B-Diffusers": TurboDiffusionT2V_1_3B_Config,
+    "loayrashid/TurboWan2.1-T2V-14B-Diffusers": TurboDiffusionT2V_14B_Config,
+    "loayrashid/TurboWan2.2-I2V-A14B-Diffusers": TurboDiffusionI2V_A14B_Config,
     # Add other specific weight variants
 }
 
@@ -109,7 +116,7 @@ PIPELINE_FALLBACK_CONFIG: dict[str, type[PipelineConfig]] = {
     "wandmdpipeline": FastWan2_1_T2V_480P_Config,
     "wancausaldmdpipeline": SelfForcingWanT2V480PConfig,
     "stepvideo": StepVideoT2VConfig,
-    "turbodiffusion": Wan2_2_I2V_A14B_Config,
+    "turbodiffusion": TurboDiffusionT2V_1_3B_Config,
     # Other fallbacks by architecture
 }
 

fastvideo/configs/pipelines/turbodiffusion.py

@@ -0,0 +1,128 @@
+# SPDX-License-Identifier: Apache-2.0
+"""
+TurboDiffusion pipeline configurations.
+
+TurboDiffusion uses RCM (recurrent Consistency Model) scheduler with
+SLA (Sparse-Linear Attention) for fast 1-4 step video generation.
+"""
+from dataclasses import dataclass, field
+
+from fastvideo.configs.models import DiTConfig, EncoderConfig, VAEConfig
+from fastvideo.configs.models.dits import WanVideoConfig
+from fastvideo.configs.models.encoders import CLIPVisionConfig
+from fastvideo.configs.models.vaes import WanVAEConfig
+from fastvideo.configs.pipelines.base import PipelineConfig
+from fastvideo.configs.pipelines.wan import t5_postprocess_text, T5Config, BaseEncoderOutput
+
+import torch
+from collections.abc import Callable
+
+
+@dataclass
+class TurboDiffusionT2VConfig(PipelineConfig):
+    """Base configuration for TurboDiffusion T2V pipeline.
+    
+    Uses RCM scheduler with sigma_max=80 for 1-4 step generation.
+    No boundary_ratio (single model, no switching).
+    """
+    # DiT
+    dit_config: DiTConfig = field(default_factory=WanVideoConfig)
+    # VAE
+    vae_config: VAEConfig = field(default_factory=WanVAEConfig)
+    vae_tiling: bool = False
+    vae_sp: bool = False
+
+    # Denoising stage
+    flow_shift: float | None = 3.0
+
+    # No boundary_ratio for T2V (single model)
+    boundary_ratio: float | None = None
+
+    # Text encoding stage
+    text_encoder_configs: tuple[EncoderConfig, ...] = field(
+        default_factory=lambda: (T5Config(), ))
+    postprocess_text_funcs: tuple[Callable[[BaseEncoderOutput], torch.Tensor],
+                                  ...] = field(default_factory=lambda:
+                                               (t5_postprocess_text, ))
+
+    # Precision for each component
+    precision: str = "bf16"
+    vae_precision: str = "fp32"
+    text_encoder_precisions: tuple[str, ...] = field(
+        default_factory=lambda: ("fp32", ))
+
+    # self-forcing params
+    warp_denoising_step: bool = True
+
+    def __post_init__(self):
+        self.vae_config.load_encoder = False
+        self.vae_config.load_decoder = True
+        # Ensure no boundary_ratio is set in dit_config
+        self.dit_config.boundary_ratio = None
+
+
+@dataclass
+class TurboDiffusionT2V_1_3B_Config(TurboDiffusionT2VConfig):
+    """Configuration for TurboDiffusion T2V 1.3B model."""
+    pass
+
+
+@dataclass
+class TurboDiffusionT2V_14B_Config(TurboDiffusionT2VConfig):
+    """Configuration for TurboDiffusion T2V 14B model.
+    
+    Uses same config as 1.3B but with higher flow_shift for 14B model.
+    """
+    flow_shift: float | None = 5.0
+
+
+@dataclass
+class TurboDiffusionI2VConfig(PipelineConfig):
+    """Base configuration for TurboDiffusion I2V pipeline.
+    
+    Uses RCM scheduler with sigma_max=200 for 1-4 step generation.
+    Uses boundary_ratio=0.9 for high-noise to low-noise model switching.
+    """
+    # DiT
+    dit_config: DiTConfig = field(default_factory=WanVideoConfig)
+    # VAE
+    vae_config: VAEConfig = field(default_factory=WanVAEConfig)
+    vae_tiling: bool = False
+    vae_sp: bool = False
+
+    # Denoising stage
+    flow_shift: float | None = 5.0
+
+    boundary_ratio: float | None = 0.9
+
+    # Text encoding stage
+    text_encoder_configs: tuple[EncoderConfig, ...] = field(
+        default_factory=lambda: (T5Config(), ))
+    postprocess_text_funcs: tuple[Callable[[BaseEncoderOutput], torch.Tensor],
+                                  ...] = field(default_factory=lambda:
+                                               (t5_postprocess_text, ))
+
+    # Image encoder for I2V
+    image_encoder_config: EncoderConfig = field(
+        default_factory=CLIPVisionConfig)
+    image_encoder_precision: str = "fp32"
+
+    # Precision for each component
+    precision: str = "bf16"
+    vae_precision: str = "fp32"
+    text_encoder_precisions: tuple[str, ...] = field(
+        default_factory=lambda: ("fp32", ))
+
+    # self-forcing params
+    warp_denoising_step: bool = True
+
+    def __post_init__(self):
+        self.vae_config.load_encoder = True
+        self.vae_config.load_decoder = True
+        self.dit_config.boundary_ratio = self.boundary_ratio
+
+
+@dataclass
+class TurboDiffusionI2V_A14B_Config(TurboDiffusionI2VConfig):
+    """Configuration for TurboDiffusion I2V A14B model."""
+    pass

fastvideo/configs/sample/registry.py

@@ -26,6 +26,11 @@ from fastvideo.configs.sample.wan import (
     SelfForcingWan2_2_T2V_A14B_480P_SamplingParam,
     MatrixGame2_SamplingParam,
 )
+from fastvideo.configs.sample.turbodiffusion import (
+    TurboDiffusionT2V_1_3B_SamplingParam,
+    TurboDiffusionT2V_14B_SamplingParam,
+    TurboDiffusionI2V_A14B_SamplingParam,
+)
 # isort: on
 from fastvideo.logger import init_logger
 from fastvideo.utils import (maybe_download_model_index,
@@ -34,36 +39,48 @@ from fastvideo.utils import (maybe_download_model_index,
 logger = init_logger(__name__)
 # Registry maps specific model weights to their config classes
 SAMPLING_PARAM_REGISTRY: dict[str, Any] = {
-    "FastVideo/FastHunyuan-diffusers": FastHunyuanSamplingParam,
-    "hunyuanvideo-community/HunyuanVideo": HunyuanSamplingParam,
+    "FastVideo/FastHunyuan-diffusers":
+    FastHunyuanSamplingParam,
+    "hunyuanvideo-community/HunyuanVideo":
+    HunyuanSamplingParam,
     "hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v":
     Hunyuan15_480P_SamplingParam,
     "hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v":
     Hunyuan15_720P_SamplingParam,
-    "FastVideo/stepvideo-t2v-diffusers": StepVideoT2VSamplingParam,
+    "FastVideo/stepvideo-t2v-diffusers":
+    StepVideoT2VSamplingParam,
 
     # Wan2.1
-    "Wan-AI/Wan2.1-T2V-1.3B-Diffusers": WanT2V_1_3B_SamplingParam,
-    "Wan-AI/Wan2.1-T2V-14B-Diffusers": WanT2V_14B_SamplingParam,
-    "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers": WanI2V_14B_480P_SamplingParam,
-    "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers": WanI2V_14B_720P_SamplingParam,
+    "Wan-AI/Wan2.1-T2V-1.3B-Diffusers":
+    WanT2V_1_3B_SamplingParam,
+    "Wan-AI/Wan2.1-T2V-14B-Diffusers":
+    WanT2V_14B_SamplingParam,
+    "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers":
+    WanI2V_14B_480P_SamplingParam,
+    "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers":
+    WanI2V_14B_720P_SamplingParam,
     "weizhou03/Wan2.1-Fun-1.3B-InP-Diffusers":
     Wan2_1_Fun_1_3B_InP_SamplingParam,
     "IRMChen/Wan2.1-Fun-1.3B-Control-Diffusers":
     Wan2_1_Fun_1_3B_Control_SamplingParam,
 
     # Wan2.2
-    "Wan-AI/Wan2.2-TI2V-5B-Diffusers": Wan2_2_TI2V_5B_SamplingParam,
+    "Wan-AI/Wan2.2-TI2V-5B-Diffusers":
+    Wan2_2_TI2V_5B_SamplingParam,
     "FastVideo/FastWan2.2-TI2V-5B-FullAttn-Diffusers":
     Wan2_2_TI2V_5B_SamplingParam,
-    "Wan-AI/Wan2.2-T2V-A14B-Diffusers": Wan2_2_T2V_A14B_SamplingParam,
-    "Wan-AI/Wan2.2-I2V-A14B-Diffusers": Wan2_2_I2V_A14B_SamplingParam,
+    "Wan-AI/Wan2.2-T2V-A14B-Diffusers":
+    Wan2_2_T2V_A14B_SamplingParam,
+    "Wan-AI/Wan2.2-I2V-A14B-Diffusers":
+    Wan2_2_I2V_A14B_SamplingParam,
 
     # FastWan2.1
-    "FastVideo/FastWan2.1-T2V-1.3B-Diffusers": FastWanT2V480P_SamplingParam,
+    "FastVideo/FastWan2.1-T2V-1.3B-Diffusers":
+    FastWanT2V480P_SamplingParam,
 
     # FastWan2.2
-    "FastVideo/FastWan2.2-TI2V-5B-Diffusers": Wan2_2_TI2V_5B_SamplingParam,
+    "FastVideo/FastWan2.2-TI2V-5B-Diffusers":
+    Wan2_2_TI2V_5B_SamplingParam,
 
     # Causal Self-Forcing Wan2.1
     "wlsaidhi/SFWan2.1-T2V-1.3B-Diffusers":
@@ -80,9 +97,20 @@ SAMPLING_PARAM_REGISTRY: dict[str, Any] = {
     Cosmos_Predict2_2B_Video2World_SamplingParam,
 
     # MatrixGame2.0 models
-    "FastVideo/Matrix-Game-2.0-Base-Diffusers": MatrixGame2_SamplingParam,
-    "FastVideo/Matrix-Game-2.0-GTA-Diffusers": MatrixGame2_SamplingParam,
-    "FastVideo/Matrix-Game-2.0-TempleRun-Diffusers": MatrixGame2_SamplingParam,
+    "FastVideo/Matrix-Game-2.0-Base-Diffusers":
+    MatrixGame2_SamplingParam,
+    "FastVideo/Matrix-Game-2.0-GTA-Diffusers":
+    MatrixGame2_SamplingParam,
+    "FastVideo/Matrix-Game-2.0-TempleRun-Diffusers":
+    MatrixGame2_SamplingParam,
+
+    # TurboDiffusion models
+    "loayrashid/TurboWan2.1-T2V-1.3B-Diffusers":
+    TurboDiffusionT2V_1_3B_SamplingParam,
+    "loayrashid/TurboWan2.1-T2V-14B-Diffusers":
+    TurboDiffusionT2V_14B_SamplingParam,
+    "loayrashid/TurboWan2.2-I2V-A14B-Diffusers":
+    TurboDiffusionI2V_A14B_SamplingParam,
 
     # Add other specific weight variants
 }
@@ -105,6 +133,8 @@ SAMPLING_PARAM_DETECTOR: dict[str, Callable[[str], bool]] = {
     lambda id: "wancausaldmdpipeline" in id.lower(),
     "matrixgame":
     lambda id: "matrixgame" in id.lower() or "matrix-game" in id.lower(),
+    "turbodiffusion":
+    lambda id: "turbodiffusion" in id.lower() or "turbowan" in id.lower(),
     # Add other pipeline architecture detectors
 }
 
@@ -121,6 +151,8 @@ SAMPLING_FALLBACK_PARAM: dict[str, Any] = {
     "wancausaldmdpipeline": SelfForcingWan2_1_T2V_1_3B_480P_SamplingParam,
     "stepvideo": StepVideoT2VSamplingParam,
     "matrixgame": MatrixGame2_SamplingParam,
+    "turbodiffusion":
+    TurboDiffusionT2V_1_3B_SamplingParam,  # Default to T2V for fallback
     # Other fallbacks by architecture
 }
 

fastvideo/configs/sample/turbodiffusion.py

@@ -0,0 +1,73 @@
+# SPDX-License-Identifier: Apache-2.0
+"""
+TurboDiffusion sampling parameters.
+
+TurboDiffusion uses RCM (recurrent Consistency Model) scheduler for
+1-4 step video generation with no classifier-free guidance.
+"""
+from dataclasses import dataclass
+
+from fastvideo.configs.sample.base import SamplingParam
+
+
+@dataclass
+class TurboDiffusionT2V_1_3B_SamplingParam(SamplingParam):
+    """Sampling parameters for TurboDiffusion T2V 1.3B model.
+    
+    Uses 4-step RCM sampling with guidance_scale=1.0 (no CFG).
+    """
+    # Video parameters
+    height: int = 480
+    width: int = 832
+    num_frames: int = 81
+    fps: int = 16
+
+    # Denoising stage - TurboDiffusion uses 1-4 steps with no CFG
+    guidance_scale: float = 1.0
+    num_inference_steps: int = 4
+
+    # No negative prompt needed for TurboDiffusion (no CFG)
+    negative_prompt: str | None = None
+
+
+@dataclass
+class TurboDiffusionT2V_14B_SamplingParam(SamplingParam):
+    """Sampling parameters for TurboDiffusion T2V 14B model.
+    
+    Uses 4-step RCM sampling with guidance_scale=1.0 (no CFG).
+    """
+    # Video parameters (720p for 14B)
+    height: int = 720
+    width: int = 1280
+    num_frames: int = 81
+    fps: int = 16
+
+    # Denoising stage - TurboDiffusion uses 1-4 steps with no CFG
+    guidance_scale: float = 1.0
+    num_inference_steps: int = 4
+
+    # No negative prompt needed for TurboDiffusion (no CFG)
+    negative_prompt: str | None = None
+
+
+@dataclass
+class TurboDiffusionI2V_A14B_SamplingParam(SamplingParam):
+    """Sampling parameters for TurboDiffusion I2V A14B model.
+    
+    Uses 4-step RCM sampling with dual-model switching (high/low noise).
+    """
+    # Video parameters (720p for A14B I2V)
+    height: int = 720
+    width: int = 1280
+    num_frames: int = 81
+    fps: int = 16
+
+    # Denoising stage - TurboDiffusion uses 1-4 steps with no CFG
+    guidance_scale: float = 1.0
+    num_inference_steps: int = 4
+
+    # Note: boundary_ratio is set in the pipeline config (TurboDiffusionI2VConfig),
+    # not here. This keeps sampling params and pipeline config separate.
+
+    # No negative prompt needed for TurboDiffusion (no CFG)
+    negative_prompt: str | None = None

fastvideo/fastvideo_args.py

@@ -132,7 +132,7 @@ class FastVideoArgs:
 
     # CPU offload parameters
     dit_cpu_offload: bool = True
-    use_fsdp_inference: bool = True
+    use_fsdp_inference: bool = False
     dit_layerwise_offload: bool = False
     text_encoder_cpu_offload: bool = True
     image_encoder_cpu_offload: bool = True
@@ -431,7 +431,9 @@ class FastVideoArgs:
             "--use-fsdp-inference",
             action=StoreBoolean,
             help=
-            "Use FSDP for inference by sharding the model weights. Latency is very low due to prefetch--enable if run out of memory.",
+            "Use FSDP for inference by sharding the model weights. FSDP helps reduce GPU memory usage but may introduce"
+            +
+            " weight transfer overhead depending on the specific setup. Enable if run out of memory.",
         )
         parser.add_argument(
             "--text-encoder-cpu-offload",

fastvideo/tests/ssim/L40S_reference_videos/TurboWan2.2-I2V-A14B-Diffusers/SLA_ATTN/steps4_An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space reali_ssim.json

@@ -0,0 +1,11 @@
+{
+  "mean_ssim": 0.9805062346988254,
+  "min_ssim": 0.9636241793632507,
+  "max_ssim": 0.9951534271240234,
+  "reference_video": "/mnt/fast-disks/hao_lab/loay/FastVideo/fastvideo/tests/ssim/L40S_reference_videos/TurboWan2.2-I2V-A14B-Diffusers/SLA_ATTN/An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space reali.mp4",
+  "generated_video": "/mnt/fast-disks/hao_lab/loay/FastVideo/fastvideo/tests/ssim/generated_videos/TurboWan2.2-I2V-A14B-Diffusers/SLA_ATTN/An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space reali.mp4",
+  "parameters": {
+    "num_inference_steps": 4,
+    "prompt": "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
+  }
+}

fastvideo/tests/ssim/generated_videos/TurboWan2.1-T2V-1.3B-Diffusers/SLA_ATTN/steps4_Will Smith casually eats noodles, his relaxed demeanor contrasting with the energetic background of _ssim.json

@@ -1,9 +1,9 @@
 {
-  "mean_ssim": 1.0,
-  "min_ssim": 1.0,
-  "max_ssim": 1.0,
-  "reference_video": "/FastVideo/fastvideo/tests/ssim/L40S_reference_videos/TurboWan2.1-T2V-1.3B-Diffusers/SLA_ATTN/Will Smith casually eats noodles, his relaxed demeanor contrasting with the energetic background of.mp4",
-  "generated_video": "/FastVideo/fastvideo/tests/ssim/generated_videos/TurboWan2.1-T2V-1.3B-Diffusers/SLA_ATTN/Will Smith casually eats noodles, his relaxed demeanor contrasting with the energetic background of.mp4",
+  "mean_ssim": 0.7606927804004999,
+  "min_ssim": 0.7035917639732361,
+  "max_ssim": 0.7920367121696472,
+  "reference_video": "/mnt/fast-disks/hao_lab/loay/FastVideo/fastvideo/tests/ssim/L40S_reference_videos/TurboWan2.1-T2V-1.3B-Diffusers/SLA_ATTN/Will Smith casually eats noodles, his relaxed demeanor contrasting with the energetic background of.mp4",
+  "generated_video": "/mnt/fast-disks/hao_lab/loay/FastVideo/fastvideo/tests/ssim/generated_videos/TurboWan2.1-T2V-1.3B-Diffusers/SLA_ATTN/Will Smith casually eats noodles, his relaxed demeanor contrasting with the energetic background of.mp4",
   "parameters": {
     "num_inference_steps": 4,
     "prompt": "Will Smith casually eats noodles, his relaxed demeanor contrasting with the energetic background of a bustling street food market. The scene captures a mix of humor and authenticity. Mid-shot framing, vibrant lighting."

fastvideo/tests/ssim/generated_videos/TurboWan2.2-I2V-A14B-Diffusers/SLA_ATTN/steps4_An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space reali_ssim.json

@@ -1,11 +0,0 @@
-{
-  "mean_ssim": 1.0,
-  "min_ssim": 1.0,
-  "max_ssim": 1.0,
-  "reference_video": "/FastVideo/fastvideo/tests/ssim/L40S_reference_videos/TurboWan2.2-I2V-A14B-Diffusers/SLA_ATTN/An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space reali.mp4",
-  "generated_video": "/FastVideo/fastvideo/tests/ssim/generated_videos/TurboWan2.2-I2V-A14B-Diffusers/SLA_ATTN/An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space reali.mp4",
-  "parameters": {
-    "num_inference_steps": 4,
-    "prompt": "An astronaut hatching from an egg, on the surface of the moon, the darkness and depth of space realised in the background. High quality, ultrarealistic detail and breath-taking movie-like camera shot."
-  }
-}

fastvideo/tests/ssim/test_turbodiffusion_similarity.py

@@ -161,7 +161,7 @@ def test_turbodiffusion_inference_similarity(prompt, model_id):
 
 # TurboDiffusion I2V parameters (dual-model with RCM scheduler + SLA attention)
 TURBODIFFUSION_I2V_PARAMS = {
-    "num_gpus": 2,
+    "num_gpus": 4,
     "model_path": "loayrashid/TurboWan2.2-I2V-A14B-Diffusers",
     "height": 480,
     "width": 832,
@@ -169,7 +169,7 @@ TURBODIFFUSION_I2V_PARAMS = {
     "num_inference_steps": 4,  # TurboDiffusion uses 1-4 steps
     "guidance_scale": 1.0,  # No CFG for TurboDiffusion
     "seed": 42,
-    "sp_size": 2,
+    "sp_size": 4,
     "tp_size": 1,
     "fps": 24,
 }
@@ -218,6 +218,8 @@ def test_turbodiffusion_i2v_inference_similarity(prompt, model_id):
         "sp_size": BASE_PARAMS["sp_size"],
         "tp_size": BASE_PARAMS["tp_size"],
         "override_pipeline_cls_name": "TurboDiffusionI2VPipeline",
+        # Keep both transformers in VRAM - avoids CPU RAM bottleneck
+        "dit_cpu_offload": False,
     }
 
     generation_kwargs = {

mkdocs.yml

@@ -153,6 +153,8 @@ nav:
     - Video Sparse Attention: attention/vsa/index.md
     - Sliding Tile Attention: attention/sta/index.md
     - Adding a New Attention Backend: attention/developer/index.md
+  - Utilities:
+    - LoRA: utilities/lora.md
   - Design:
     - Overview: design/overview.md
   - Developer Guide:

pyproject.toml

@@ -111,7 +111,7 @@ lint = [
 ]
 
 test = [
-    "av==14.3.0",
+    "av",
     "pytorch-msssim==1.0.0",
     "pytest",
 ]

pyproject_other.toml

@@ -90,7 +90,7 @@ lint = [
 ]
 
 test = [
-    "av==14.3.0",
+    "av",
     "pytorch-msssim==1.0.0",
     "pytest",
 ]