diff --git a/README.md b/README.md index 78e89ff..5a89111 100644 --- a/README.md +++ b/README.md @@ -398,7 +398,7 @@ Example code for Anima is located at: [/examples/anima/](/examples/anima/) | Model ID | Inference | Low VRAM Inference | Full Training | Validation after Full Training | LoRA Training | Validation after LoRA Training | |-|-|-|-|-|-|-| -|[circlestone-labs/Anima](https://www.modelscope.cn/models/circlestone-labs/Anima)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_inference/anima-preview.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_inference_low_vram/anima-preview.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_training/full/anima-preview.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_training/validate_full/anima-preview.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_training/lora/anima-preview.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_training/validate_lora/anima-preview.py)| +|[circlestone-labs/Anima](https://www.modelscope.cn/models/circlestone-labs/Anima)|[code](/examples/anima/model_inference/anima-preview.py)|[code](/examples/anima/model_inference_low_vram/anima-preview.py)|[code](/examples/anima/model_training/full/anima-preview.sh)|[code](/examples/anima/model_training/validate_full/anima-preview.py)|[code](/examples/anima/model_training/lora/anima-preview.sh)|[code](/examples/anima/model_training/validate_lora/anima-preview.py)| @@ -705,6 +705,12 @@ Example code for LTX-2 is available at: [/examples/ltx2/](/examples/ltx2/) | Model ID | Extra Args | Inference | Low-VRAM Inference | Full Training | Full Training Validation | LoRA Training | LoRA Training Validation | |-|-|-|-|-|-|-|-| +|[Lightricks/LTX-2.3: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](/examples/ltx2/model_inference/LTX-2.3-I2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: TwoStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](/examples/ltx2/model_inference/LTX-2.3-I2AV-TwoStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: DistilledPipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](/examples/ltx2/model_inference/LTX-2.3-I2AV-DistilledPipeline.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-DistilledPipeline.py)|-|-|-|-| +|[Lightricks/LTX-2.3: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](/examples/ltx2/model_inference/LTX-2.3-T2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-OneStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: TwoStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](/examples/ltx2/model_inference/LTX-2.3-T2AV-TwoStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-TwoStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](/examples/ltx2/model_inference/LTX-2.3-T2AV-DistilledPipeline.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-DistilledPipeline.py)|-|-|-|-| |[Lightricks/LTX-2: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](/examples/ltx2/model_inference/LTX-2-T2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-OneStage.py)|[code](/examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh)|[code](/examples/ltx2/model_training/validate_full/LTX-2-T2AV.py)|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py)| |[Lightricks/LTX-2-19b-IC-LoRA-Union-Control](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Union-Control)|`in_context_videos`,`in_context_downsample_factor`|[code](/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Union-Control.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Union-Control.py)|-|-|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)| |[Lightricks/LTX-2-19b-IC-LoRA-Detailer](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer)|`in_context_videos`,`in_context_downsample_factor`|[code](/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Detailer.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Detailer.py)|-|-|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)| diff --git a/README_zh.md b/README_zh.md index c2d8bb6..fec510a 100644 --- a/README_zh.md +++ b/README_zh.md @@ -398,7 +398,7 @@ Anima 的示例代码位于：[/examples/anima/](/examples/anima/) |模型 ID|推理|低显存推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证| |-|-|-|-|-|-|-| -|[circlestone-labs/Anima](https://www.modelscope.cn/models/circlestone-labs/Anima)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_inference/anima-preview.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_inference_low_vram/anima-preview.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_training/full/anima-preview.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_training/validate_full/anima-preview.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_training/lora/anima-preview.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/anima/model_training/validate_lora/anima-preview.py)| +|[circlestone-labs/Anima](https://www.modelscope.cn/models/circlestone-labs/Anima)|[code](/examples/anima/model_inference/anima-preview.py)|[code](/examples/anima/model_inference_low_vram/anima-preview.py)|[code](/examples/anima/model_training/full/anima-preview.sh)|[code](/examples/anima/model_training/validate_full/anima-preview.py)|[code](/examples/anima/model_training/lora/anima-preview.sh)|[code](/examples/anima/model_training/validate_lora/anima-preview.py)| @@ -705,6 +705,12 @@ LTX-2 的示例代码位于：[/examples/ltx2/](/examples/ltx2/) |模型 ID|额外参数|推理|低显存推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证| |-|-|-|-|-|-|-|-| +|[Lightricks/LTX-2.3: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](/examples/ltx2/model_inference/LTX-2.3-I2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: TwoStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](/examples/ltx2/model_inference/LTX-2.3-I2AV-TwoStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: DistilledPipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](/examples/ltx2/model_inference/LTX-2.3-I2AV-DistilledPipeline.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-DistilledPipeline.py)|-|-|-|-| +|[Lightricks/LTX-2.3: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](/examples/ltx2/model_inference/LTX-2.3-T2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-OneStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: TwoStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](/examples/ltx2/model_inference/LTX-2.3-T2AV-TwoStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-TwoStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](/examples/ltx2/model_inference/LTX-2.3-T2AV-DistilledPipeline.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-DistilledPipeline.py)|-|-|-|-| |[Lightricks/LTX-2: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](/examples/ltx2/model_inference/LTX-2-T2AV-OneStage.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-OneStage.py)|[code](/examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh)|[code](/examples/ltx2/model_training/validate_full/LTX-2-T2AV.py)|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py)| |[Lightricks/LTX-2-19b-IC-LoRA-Union-Control](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Union-Control)|`in_context_videos`,`in_context_downsample_factor`|[code](/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Union-Control.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Union-Control.py)|-|-|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)| |[Lightricks/LTX-2-19b-IC-LoRA-Detailer](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer)|`in_context_videos`,`in_context_downsample_factor`|[code](/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Detailer.py)|[code](/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Detailer.py)|-|-|[code](/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)| diff --git a/diffsynth/configs/model_configs.py b/diffsynth/configs/model_configs.py index bfe2fe3..3c00dca 100644 --- a/diffsynth/configs/model_configs.py +++ b/diffsynth/configs/model_configs.py @@ -768,7 +768,7 @@ ltx2_series = [ "model_hash": "f3a83ecf3995dcc4fae2d27e08ad5767", "model_name": "ltx2_text_encoder_post_modules", "model_class": "diffsynth.models.ltx2_text_encoder.LTX2TextEncoderPostModules", - "extra_kwargs": {"seperated_audio_video": True, "embedding_dim_gemma": 3840, "num_layers_gemma": 49, "video_attetion_heads": 32, "video_attention_head_dim": 128, "audio_attention_heads": 32, "audio_attention_head_dim": 64, "num_connetor_layers": 8, "apply_gated_attention": True}, + "extra_kwargs": {"separated_audio_video": True, "embedding_dim_gemma": 3840, "num_layers_gemma": 49, "video_attention_heads": 32, "video_attention_head_dim": 128, "audio_attention_heads": 32, "audio_attention_head_dim": 64, "num_connector_layers": 8, "apply_gated_attention": True}, "state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_text_encoder.LTX2TextEncoderPostModulesStateDictConverter", }, { diff --git a/diffsynth/models/ltx2_text_encoder.py b/diffsynth/models/ltx2_text_encoder.py index c67ce90..e4f3b1a 100644 --- a/diffsynth/models/ltx2_text_encoder.py +++ b/diffsynth/models/ltx2_text_encoder.py @@ -406,36 +406,36 @@ class Embeddings1DConnector(nn.Module): class LTX2TextEncoderPostModules(nn.Module): def __init__( self, - seperated_audio_video: bool = False, + separated_audio_video: bool = False, embedding_dim_gemma: int = 3840, num_layers_gemma: int = 49, - video_attetion_heads: int = 32, + video_attention_heads: int = 32, video_attention_head_dim: int = 128, audio_attention_heads: int = 32, audio_attention_head_dim: int = 64, - num_connetor_layers: int = 2, + num_connector_layers: int = 2, apply_gated_attention: bool = False, ): super().__init__() - if not seperated_audio_video: + if not separated_audio_video: self.feature_extractor_linear = GemmaFeaturesExtractorProjLinear() self.embeddings_connector = Embeddings1DConnector() self.audio_embeddings_connector = Embeddings1DConnector() else: # LTX-2.3 self.feature_extractor_linear = GemmaSeperatedFeaturesExtractorProjLinear( - num_layers_gemma, embedding_dim_gemma, video_attetion_heads * video_attention_head_dim, + num_layers_gemma, embedding_dim_gemma, video_attention_heads * video_attention_head_dim, audio_attention_heads * audio_attention_head_dim) self.embeddings_connector = Embeddings1DConnector( attention_head_dim=video_attention_head_dim, - num_attention_heads=video_attetion_heads, - num_layers=num_connetor_layers, + num_attention_heads=video_attention_heads, + num_layers=num_connector_layers, apply_gated_attention=apply_gated_attention, ) self.audio_embeddings_connector = Embeddings1DConnector( attention_head_dim=audio_attention_head_dim, num_attention_heads=audio_attention_heads, - num_layers=num_connetor_layers, + num_layers=num_connector_layers, apply_gated_attention=apply_gated_attention, ) diff --git a/diffsynth/pipelines/ltx2_audio_video.py b/diffsynth/pipelines/ltx2_audio_video.py index d3802fa..783c75d 100644 --- a/diffsynth/pipelines/ltx2_audio_video.py +++ b/diffsynth/pipelines/ltx2_audio_video.py @@ -413,7 +413,7 @@ class LTX2AudioVideoUnit_InputAudioEmbedder(PipelineUnit): class LTX2AudioVideoUnit_InputImagesEmbedder(PipelineUnit): def __init__(self): super().__init__( - input_params=("input_images", "input_images_indexes", "input_images_strength", "video_latents", "height", "width", "num_frames", "tiled", "tile_size_in_pixels", "tile_overlap_in_pixels", "use_two_stage_pipeline"), + input_params=("input_images", "input_images_indexes", "input_images_strength", "video_latents", "height", "width", "tiled", "tile_size_in_pixels", "tile_overlap_in_pixels", "use_two_stage_pipeline"), output_params=("video_latents", "denoise_mask_video", "input_latents_video", "stage2_input_latents"), onload_model_names=("video_vae_encoder") ) @@ -426,7 +426,7 @@ class LTX2AudioVideoUnit_InputImagesEmbedder(PipelineUnit): latent = pipe.video_vae_encoder.encode(image, tiled, tile_size_in_pixels, tile_overlap_in_pixels).to(pipe.device) return latent - def process(self, pipe: LTX2AudioVideoPipeline, input_images, input_images_indexes, input_images_strength, video_latents, height, width, num_frames, tiled, tile_size_in_pixels, tile_overlap_in_pixels, use_two_stage_pipeline=False): + def process(self, pipe: LTX2AudioVideoPipeline, input_images, input_images_indexes, input_images_strength, video_latents, height, width, tiled, tile_size_in_pixels, tile_overlap_in_pixels, use_two_stage_pipeline=False): if input_images is None or len(input_images) == 0: return {"video_latents": video_latents} else: diff --git a/docs/en/Model_Details/LTX-2.md b/docs/en/Model_Details/LTX-2.md index 0123dfe..007d0b7 100644 --- a/docs/en/Model_Details/LTX-2.md +++ b/docs/en/Model_Details/LTX-2.md @@ -111,6 +111,12 @@ write_video_audio_ltx2( ## Model Overview |Model ID|Additional Parameters|Inference|Low VRAM Inference|Full Training|Validation After Full Training|LoRA Training|Validation After LoRA Training| |-|-|-|-|-|-|-|-| +|[Lightricks/LTX-2.3: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-I2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: TwoStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-I2AV-TwoStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: DistilledPipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-I2AV-DistilledPipeline.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-DistilledPipeline.py)|-|-|-|-| +|[Lightricks/LTX-2.3: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-OneStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: TwoStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-T2AV-TwoStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-TwoStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-T2AV-DistilledPipeline.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-DistilledPipeline.py)|-|-|-|-| |[Lightricks/LTX-2: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_full/LTX-2-T2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py)| |[Lightricks/LTX-2-19b-IC-LoRA-Union-Control](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Union-Control)|`in_context_videos`,`in_context_downsample_factor`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Union-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Union-Control.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)| |[Lightricks/LTX-2-19b-IC-LoRA-Detailer](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer)|`in_context_videos`,`in_context_downsample_factor`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Detailer.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Detailer.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)| diff --git a/docs/zh/Model_Details/LTX-2.md b/docs/zh/Model_Details/LTX-2.md index 0c23adb..66755db 100644 --- a/docs/zh/Model_Details/LTX-2.md +++ b/docs/zh/Model_Details/LTX-2.md @@ -111,6 +111,12 @@ write_video_audio_ltx2( ## 模型总览 |模型 ID|额外参数|推理|低显存推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证| |-|-|-|-|-|-|-|-| +|[Lightricks/LTX-2.3: OneStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-I2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: TwoStagePipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-I2AV-TwoStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: DistilledPipeline-I2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)|`input_images`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-I2AV-DistilledPipeline.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-DistilledPipeline.py)|-|-|-|-| +|[Lightricks/LTX-2.3: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-OneStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: TwoStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-T2AV-TwoStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-TwoStage.py)|-|-|-|-| +|[Lightricks/LTX-2.3: DistilledPipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2.3)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2.3-T2AV-DistilledPipeline.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-DistilledPipeline.py)|-|-|-|-| |[Lightricks/LTX-2: OneStagePipeline-T2AV](https://www.modelscope.cn/models/Lightricks/LTX-2)||[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-OneStage.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/full/LTX-2-T2AV-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_full/LTX-2-T2AV.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV.py)| |[Lightricks/LTX-2-19b-IC-LoRA-Union-Control](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Union-Control)|`in_context_videos`,`in_context_downsample_factor`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Union-Control.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Union-Control.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)| |[Lightricks/LTX-2-19b-IC-LoRA-Detailer](https://www.modelscope.cn/models/Lightricks/LTX-2-19b-IC-LoRA-Detailer)|`in_context_videos`,`in_context_downsample_factor`|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference/LTX-2-T2AV-IC-LoRA-Detailer.py)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_inference_low_vram/LTX-2-T2AV-IC-LoRA-Detailer.py)|-|-|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/lora/LTX-2-T2AV-IC-LoRA-splited.sh)|[code](https://github.com/modelscope/DiffSynth-Studio/blob/main/examples/ltx2/model_training/validate_lora/LTX-2-T2AV-IC-LoRA.py)| diff --git a/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-DistilledPipeline.py b/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-DistilledPipeline.py new file mode 100644 index 0000000..5585efc --- /dev/null +++ b/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-DistilledPipeline.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.float8_e5m2, + "offload_device": "cpu", + "onload_dtype": torch.float8_e5m2, + "onload_device": "cpu", + "preparing_dtype": torch.float8_e5m2, + "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"), + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, +) + + +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, +) diff --git a/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.py b/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.py new file mode 100644 index 0000000..8c18563 --- /dev/null +++ b/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-OneStage.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 +from PIL import Image +from modelscope import dataset_snapshot_download + +vram_config = { + "offload_dtype": torch.float8_e5m2, + "offload_device": "cpu", + "onload_dtype": torch.float8_e5m2, + "onload_device": "cpu", + "preparing_dtype": torch.float8_e5m2, + "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"), + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, +) + +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, +) diff --git a/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py b/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py new file mode 100644 index 0000000..ad2dd7e --- /dev/null +++ b/examples/ltx2/model_inference_low_vram/LTX-2.3-I2AV-TwoStage.py @@ -0,0 +1,72 @@ +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.float8_e5m2, + "offload_device": "cpu", + "onload_dtype": torch.float8_e5m2, + "onload_device": "cpu", + "preparing_dtype": torch.float8_e5m2, + "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"), + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, +) + +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, +) diff --git a/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-DistilledPipeline.py b/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-DistilledPipeline.py new file mode 100644 index 0000000..8d67de9 --- /dev/null +++ b/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-DistilledPipeline.py @@ -0,0 +1,58 @@ +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.float8_e5m2, + "offload_device": "cpu", + "onload_dtype": torch.float8_e5m2, + "onload_device": "cpu", + "preparing_dtype": torch.float8_e5m2, + "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"), + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, +) + +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, +) diff --git a/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-OneStage.py b/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-OneStage.py new file mode 100644 index 0000000..95fa5ca --- /dev/null +++ b/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-OneStage.py @@ -0,0 +1,43 @@ +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.float8_e5m2, + "offload_device": "cpu", + "onload_dtype": torch.float8_e5m2, + "onload_device": "cpu", + "preparing_dtype": torch.float8_e5m2, + "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"), + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, +) +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, +) diff --git a/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-TwoStage.py b/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-TwoStage.py new file mode 100644 index 0000000..a954b40 --- /dev/null +++ b/examples/ltx2/model_inference_low_vram/LTX-2.3-T2AV-TwoStage.py @@ -0,0 +1,58 @@ +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.float8_e5m2, + "offload_device": "cpu", + "onload_dtype": torch.float8_e5m2, + "onload_device": "cpu", + "preparing_dtype": torch.float8_e5m2, + "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"), + vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5, +) +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, +)