support ltx2.3 inference

examples/ltx2/model_inference/LTX-2-I2AV-OneStage.py

@@ -30,7 +30,7 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
 )
 prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
 negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
-height, width, num_frames = 512 * 2, 768 * 2, 121
+height, width, num_frames = 512, 768, 121
 dataset_snapshot_download(
     dataset_id="DiffSynth-Studio/examples_in_diffsynth",
     local_dir="./",

examples/ltx2/model_inference/LTX-2.3-I2AV-DistilledPipeline.py

@@ -0,0 +1,70 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+from PIL import Image
+from modelscope import dataset_snapshot_download
+
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cpu",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-spatial-upscaler-x2-1.0.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+)
+
+
+prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
+negative_prompt = (
+    "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, "
+    "grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, "
+    "deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, "
+    "wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of "
+    "field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent "
+    "lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny "
+    "valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, "
+    "mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, "
+    "off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward "
+    "pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, "
+    "inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+)
+height, width, num_frames = 512 * 2, 768 * 2, 121
+dataset_snapshot_download(
+    dataset_id="DiffSynth-Studio/examples_in_diffsynth",
+    local_dir="./",
+    allow_file_pattern=["data/examples/ltx-2/first_frame.jpg"]
+)
+image = Image.open("data/examples/ltx-2/first_frame.jpg").convert("RGB").resize((width, height))
+# first frame
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    tiled=True,
+    use_distilled_pipeline=True,
+    input_images=[image],
+    input_images_indexes=[0],
+    input_images_strength=1.0,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2.3_distilled_i2av_first.mp4',
+    fps=24,
+    audio_sample_rate=pipe.audio_vocoder.output_sampling_rate,
+)

examples/ltx2/model_inference/LTX-2.3-I2AV-OneStage.py

@@ -0,0 +1,56 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+from PIL import Image
+from modelscope import dataset_snapshot_download
+
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cpu",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+)
+
+prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
+negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+height, width, num_frames = 512, 768, 121
+dataset_snapshot_download(
+    dataset_id="DiffSynth-Studio/examples_in_diffsynth",
+    local_dir="./",
+    allow_file_pattern=["data/examples/ltx-2/first_frame.jpg"]
+)
+image = Image.open("data/examples/ltx-2/first_frame.jpg").convert("RGB").resize((width, height))
+# first frame
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    tiled=False,
+    input_images=[image],
+    input_images_indexes=[0],
+    input_images_strength=1.0,
+    num_inference_steps=40,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2.3_onestage_i2av_first.mp4',
+    fps=24,
+    audio_sample_rate=pipe.audio_vocoder.output_sampling_rate,
+)

examples/ltx2/model_inference/LTX-2.3-I2AV-TwoStage.py

@@ -0,0 +1,71 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+from PIL import Image
+from modelscope import dataset_snapshot_download
+
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cpu",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-spatial-upscaler-x2-1.0.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+    stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled-lora-384.safetensors"),
+)
+
+prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
+negative_prompt = (
+    "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, "
+    "grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, "
+    "deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, "
+    "wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of "
+    "field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent "
+    "lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny "
+    "valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, "
+    "mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, "
+    "off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward "
+    "pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, "
+    "inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+)
+height, width, num_frames = 512 * 2, 768 * 2, 121
+dataset_snapshot_download(
+    dataset_id="DiffSynth-Studio/examples_in_diffsynth",
+    local_dir="./",
+    allow_file_pattern=["data/examples/ltx-2/first_frame.jpg"]
+)
+image = Image.open("data/examples/ltx-2/first_frame.jpg").convert("RGB").resize((width, height))
+# first frame
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=42,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    tiled=True,
+    use_two_stage_pipeline=True,
+    num_inference_steps=40,
+    input_images=[image],
+    input_images_indexes=[0],
+    input_images_strength=1.0,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2.3_twostage_i2av_first.mp4',
+    fps=24,
+    audio_sample_rate=pipe.audio_vocoder.output_sampling_rate,
+)

examples/ltx2/model_inference/LTX-2.3-T2AV-DistilledPipeline.py

@@ -0,0 +1,57 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cpu",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-spatial-upscaler-x2-1.0.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+)
+
+prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
+negative_prompt = (
+    "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, "
+    "grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, "
+    "deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, "
+    "wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of "
+    "field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent "
+    "lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny "
+    "valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, "
+    "mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, "
+    "off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward "
+    "pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, "
+    "inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+)
+height, width, num_frames = 512 * 2, 768 * 2, 121
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    tiled=True,
+    use_distilled_pipeline=True,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2.3_distilled.mp4',
+    fps=24,
+    audio_sample_rate=pipe.audio_vocoder.output_sampling_rate,
+)

examples/ltx2/model_inference/LTX-2.3-T2AV-OneStage.py

@@ -0,0 +1,42 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cpu",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+)
+prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
+negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+height, width, num_frames = 512, 768, 121
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    tiled=True,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2.3_onestage.mp4',
+    fps=24,
+    audio_sample_rate=pipe.audio_vocoder.output_sampling_rate,
+)

examples/ltx2/model_inference/LTX-2.3-T2AV-TwoStage.py

@@ -0,0 +1,57 @@
+import torch
+from diffsynth.pipelines.ltx2_audio_video import LTX2AudioVideoPipeline, ModelConfig
+from diffsynth.utils.data.media_io_ltx2 import write_video_audio_ltx2
+
+vram_config = {
+    "offload_dtype": torch.bfloat16,
+    "offload_device": "cpu",
+    "onload_dtype": torch.bfloat16,
+    "onload_device": "cuda",
+    "preparing_dtype": torch.bfloat16,
+    "preparing_device": "cuda",
+    "computation_dtype": torch.bfloat16,
+    "computation_device": "cuda",
+}
+pipe = LTX2AudioVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors", **vram_config),
+        ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-spatial-upscaler-x2-1.0.safetensors", **vram_config),
+    ],
+    tokenizer_config=ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized"),
+    stage2_lora_config=ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-distilled-lora-384.safetensors"),
+)
+prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
+negative_prompt = (
+    "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, "
+    "grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, "
+    "deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, "
+    "wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of "
+    "field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent "
+    "lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny "
+    "valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, "
+    "mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, "
+    "off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward "
+    "pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, "
+    "inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
+)
+height, width, num_frames = 512 * 2, 768 * 2, 121
+video, audio = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    seed=43,
+    height=height,
+    width=width,
+    num_frames=num_frames,
+    tiled=True,
+    use_two_stage_pipeline=True,
+)
+write_video_audio_ltx2(
+    video=video,
+    audio=audio,
+    output_path='ltx2.3_twostage.mp4',
+    fps=24,
+    audio_sample_rate=pipe.audio_vocoder.output_sampling_rate,
+)

examples/ltx2/model_inference_low_vram/LTX-2-I2AV-OneStage.py

@@ -31,7 +31,7 @@ pipe = LTX2AudioVideoPipeline.from_pretrained(
 )
 prompt = "A girl is very happy, she is speaking: “I enjoy working with Diffsynth-Studio, it's a perfect framework.”"
 negative_prompt = "blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts."
-height, width, num_frames = 512 * 2, 768 * 2, 121
+height, width, num_frames = 512, 768, 121
 dataset_snapshot_download(
     dataset_id="DiffSynth-Studio/examples_in_diffsynth",
     local_dir="./",