Diffusers documentation

LTX-2

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v0.36.0).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

LTX-2

LTX-2 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution.

You can find all the original LTX-Video checkpoints under the Lightricks organization.

The original codebase for LTX-2 can be found here.

LTX2Pipeline

class diffusers.LTX2Pipeline

< >

( scheduler: FlowMatchEulerDiscreteScheduler vae: AutoencoderKLLTX2Video audio_vae: AutoencoderKLLTX2Audio text_encoder: Gemma3ForConditionalGeneration tokenizer: typing.Union[transformers.models.gemma.tokenization_gemma.GemmaTokenizer, transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast] connectors: LTX2TextConnectors transformer: LTX2VideoTransformer3DModel vocoder: LTX2Vocoder )

Parameters

  • transformer (LTXVideoTransformer3DModel) — Conditional Transformer architecture to denoise the encoded video latents.
  • scheduler (FlowMatchEulerDiscreteScheduler) — A scheduler to be used in combination with transformer to denoise the encoded image latents.
  • vae (AutoencoderKLLTXVideo) — Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
  • text_encoder (T5EncoderModel) — T5, specifically the google/t5-v1_1-xxl variant.
  • tokenizer (CLIPTokenizer) — Tokenizer of class CLIPTokenizer.
  • tokenizer (T5TokenizerFast) — Second Tokenizer of class T5TokenizerFast.
  • connectors (LTX2TextConnectors) — Text connector stack used to adapt text encoder hidden states for the video and audio branches.

Pipeline for text-to-video generation.

Reference: https://github.com/Lightricks/LTX-Video

__call__

< >

( prompt: typing.Union[str, typing.List[str]] = None negative_prompt: typing.Union[str, typing.List[str], NoneType] = None height: int = 512 width: int = 768 num_frames: int = 121 frame_rate: float = 24.0 num_inference_steps: int = 40 timesteps: typing.List[int] = None guidance_scale: float = 4.0 guidance_rescale: float = 0.0 num_videos_per_prompt: typing.Optional[int] = 1 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None latents: typing.Optional[torch.Tensor] = None audio_latents: typing.Optional[torch.Tensor] = None prompt_embeds: typing.Optional[torch.Tensor] = None prompt_attention_mask: typing.Optional[torch.Tensor] = None negative_prompt_embeds: typing.Optional[torch.Tensor] = None negative_prompt_attention_mask: typing.Optional[torch.Tensor] = None decode_timestep: typing.Union[float, typing.List[float]] = 0.0 decode_noise_scale: typing.Union[float, typing.List[float], NoneType] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True attention_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = None callback_on_step_end: typing.Optional[typing.Callable[[int, int, typing.Dict], NoneType]] = None callback_on_step_end_tensor_inputs: typing.List[str] = ['latents'] max_sequence_length: int = 1024 ) ~pipelines.ltx.LTX2PipelineOutput or tuple

Parameters

  • prompt (str or List[str], optional) — The prompt or prompts to guide the image generation. If not defined, one has to pass prompt_embeds. instead.
  • height (int, optional, defaults to 512) — The height in pixels of the generated image. This is set to 480 by default for the best results.
  • width (int, optional, defaults to 768) — The width in pixels of the generated image. This is set to 848 by default for the best results.
  • num_frames (int, optional, defaults to 121) — The number of video frames to generate
  • frame_rate (float, optional, defaults to 24.0) — The frames per second (FPS) of the generated video.
  • num_inference_steps (int, optional, defaults to 40) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
  • timesteps (List[int], optional) — Custom timesteps to use for the denoising process with schedulers which support a timesteps argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. Must be in descending order.
  • guidance_scale (float, optional, defaults to 4.0) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. Guidance scale is enabled by setting guidance_scale > 1. Higher guidance scale encourages to generate images that are closely linked to the text prompt, usually at the expense of lower image quality.
  • guidance_rescale (float, optional, defaults to 0.0) — Guidance rescale factor proposed by Common Diffusion Noise Schedules and Sample Steps are Flawed guidance_scale is defined as φ in equation 16. of Common Diffusion Noise Schedules and Sample Steps are Flawed. Guidance rescale factor should fix overexposure when using zero terminal SNR.
  • num_videos_per_prompt (int, optional, defaults to 1) — The number of videos to generate per prompt.
  • generator (torch.Generator or List[torch.Generator], optional) — One or a list of torch generator(s) to make generation deterministic.
  • latents (torch.Tensor, optional) — Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will be generated by sampling using the supplied random generator.
  • audio_latents (torch.Tensor, optional) — Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for audio generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will be generated by sampling using the supplied random generator.
  • prompt_embeds (torch.Tensor, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.
  • prompt_attention_mask (torch.Tensor, optional) — Pre-generated attention mask for text embeddings.
  • negative_prompt_embeds (torch.FloatTensor, optional) — Pre-generated negative text embeddings. For PixArt-Sigma this negative prompt should be "". If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.
  • negative_prompt_attention_mask (torch.FloatTensor, optional) — Pre-generated attention mask for negative text embeddings.
  • decode_timestep (float, defaults to 0.0) — The timestep at which generated video is decoded.
  • decode_noise_scale (float, defaults to None) — The interpolation factor between random noise and denoised latents at the decode timestep.
  • output_type (str, optional, defaults to "pil") — The output format of the generate image. Choose between PIL: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.ltx.LTX2PipelineOutput instead of a plain tuple.
  • attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.models.attention_processor.
  • callback_on_step_end (Callable, optional) — A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.
  • callback_on_step_end_tensor_inputs (List, optional, defaults to ["latents"]) — The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeline class.
  • max_sequence_length (int, optional, defaults to 1024) — Maximum sequence length to use with the prompt.

Returns

~pipelines.ltx.LTX2PipelineOutput or tuple

If return_dict is True, ~pipelines.ltx.LTX2PipelineOutput is returned, otherwise a tuple is returned where the first element is a list with the generated images.

Function invoked when calling the pipeline for generation.

Examples:

>>> import torch
>>> from diffusers import LTX2Pipeline
>>> from diffusers.pipelines.ltx2.export_utils import encode_video

>>> pipe = LTX2Pipeline.from_pretrained("Lightricks/LTX-2", torch_dtype=torch.bfloat16)
>>> pipe.enable_model_cpu_offload()

>>> prompt = "A woman with long brown hair and light skin smiles at another woman with long blonde hair. The woman with brown hair wears a black jacket and has a small, barely noticeable mole on her right cheek. The camera angle is a close-up, focused on the woman with brown hair's face. The lighting is warm and natural, likely from the setting sun, casting a soft glow on the scene. The scene appears to be real-life footage"
>>> negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"

>>> frame_rate = 24.0
>>> video, audio = pipe(
...     prompt=prompt,
...     negative_prompt=negative_prompt,
...     width=768,
...     height=512,
...     num_frames=121,
...     frame_rate=frame_rate,
...     num_inference_steps=40,
...     guidance_scale=4.0,
...     output_type="np",
...     return_dict=False,
... )
>>> video = (video * 255).round().astype("uint8")
>>> video = torch.from_numpy(video)

>>> encode_video(
...     video[0],
...     fps=frame_rate,
...     audio=audio[0].float().cpu(),
...     audio_sample_rate=pipe.vocoder.config.output_sampling_rate,  # should be 24000
...     output_path="video.mp4",
... )

encode_prompt

< >

( prompt: typing.Union[str, typing.List[str]] negative_prompt: typing.Union[str, typing.List[str], NoneType] = None do_classifier_free_guidance: bool = True num_videos_per_prompt: int = 1 prompt_embeds: typing.Optional[torch.Tensor] = None negative_prompt_embeds: typing.Optional[torch.Tensor] = None prompt_attention_mask: typing.Optional[torch.Tensor] = None negative_prompt_attention_mask: typing.Optional[torch.Tensor] = None max_sequence_length: int = 1024 scale_factor: int = 8 device: typing.Optional[torch.device] = None dtype: typing.Optional[torch.dtype] = None )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
  • do_classifier_free_guidance (bool, optional, defaults to True) — Whether to use classifier free guidance or not.
  • num_videos_per_prompt (int, optional, defaults to 1) — Number of videos that should be generated per prompt. torch device to place the resulting embeddings on
  • prompt_embeds (torch.Tensor, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.
  • negative_prompt_embeds (torch.Tensor, optional) — Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.
  • device — (torch.device, optional): torch device
  • dtype — (torch.dtype, optional): torch dtype

Encodes the prompt into text encoder hidden states.

LTX2ImageToVideoPipeline

class diffusers.LTX2ImageToVideoPipeline

< >

( scheduler: FlowMatchEulerDiscreteScheduler vae: AutoencoderKLLTX2Video audio_vae: AutoencoderKLLTX2Audio text_encoder: Gemma3ForConditionalGeneration tokenizer: typing.Union[transformers.models.gemma.tokenization_gemma.GemmaTokenizer, transformers.models.gemma.tokenization_gemma_fast.GemmaTokenizerFast] connectors: LTX2TextConnectors transformer: LTX2VideoTransformer3DModel vocoder: LTX2Vocoder )

Pipeline for image-to-video generation.

Reference: https://github.com/Lightricks/LTX-Video

TODO

__call__

< >

( image: typing.Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, typing.List[PIL.Image.Image], typing.List[numpy.ndarray], typing.List[torch.Tensor]] = None prompt: typing.Union[str, typing.List[str]] = None negative_prompt: typing.Union[str, typing.List[str], NoneType] = None height: int = 512 width: int = 768 num_frames: int = 121 frame_rate: float = 24.0 num_inference_steps: int = 40 timesteps: typing.List[int] = None guidance_scale: float = 4.0 guidance_rescale: float = 0.0 num_videos_per_prompt: typing.Optional[int] = 1 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None latents: typing.Optional[torch.Tensor] = None audio_latents: typing.Optional[torch.Tensor] = None prompt_embeds: typing.Optional[torch.Tensor] = None prompt_attention_mask: typing.Optional[torch.Tensor] = None negative_prompt_embeds: typing.Optional[torch.Tensor] = None negative_prompt_attention_mask: typing.Optional[torch.Tensor] = None decode_timestep: typing.Union[float, typing.List[float]] = 0.0 decode_noise_scale: typing.Union[float, typing.List[float], NoneType] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True attention_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = None callback_on_step_end: typing.Optional[typing.Callable[[int, int, typing.Dict], NoneType]] = None callback_on_step_end_tensor_inputs: typing.List[str] = ['latents'] max_sequence_length: int = 1024 ) ~pipelines.ltx.LTX2PipelineOutput or tuple

Parameters

  • image (PipelineImageInput) — The input image to condition the generation on. Must be an image, a list of images or a torch.Tensor.
  • prompt (str or List[str], optional) — The prompt or prompts to guide the image generation. If not defined, one has to pass prompt_embeds. instead.
  • height (int, optional, defaults to 512) — The height in pixels of the generated image. This is set to 480 by default for the best results.
  • width (int, optional, defaults to 768) — The width in pixels of the generated image. This is set to 848 by default for the best results.
  • num_frames (int, optional, defaults to 121) — The number of video frames to generate
  • frame_rate (float, optional, defaults to 24.0) — The frames per second (FPS) of the generated video.
  • num_inference_steps (int, optional, defaults to 40) — The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
  • timesteps (List[int], optional) — Custom timesteps to use for the denoising process with schedulers which support a timesteps argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. Must be in descending order.
  • guidance_scale (float, optional, defaults to 4.0) — Guidance scale as defined in Classifier-Free Diffusion Guidance. guidance_scale is defined as w of equation 2. of Imagen Paper. Guidance scale is enabled by setting guidance_scale > 1. Higher guidance scale encourages to generate images that are closely linked to the text prompt, usually at the expense of lower image quality.
  • guidance_rescale (float, optional, defaults to 0.0) — Guidance rescale factor proposed by Common Diffusion Noise Schedules and Sample Steps are Flawed guidance_scale is defined as φ in equation 16. of Common Diffusion Noise Schedules and Sample Steps are Flawed. Guidance rescale factor should fix overexposure when using zero terminal SNR.
  • num_videos_per_prompt (int, optional, defaults to 1) — The number of videos to generate per prompt.
  • generator (torch.Generator or List[torch.Generator], optional) — One or a list of torch generator(s) to make generation deterministic.
  • latents (torch.Tensor, optional) — Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for video generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will be generated by sampling using the supplied random generator.
  • audio_latents (torch.Tensor, optional) — Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for audio generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will be generated by sampling using the supplied random generator.
  • prompt_embeds (torch.Tensor, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.
  • prompt_attention_mask (torch.Tensor, optional) — Pre-generated attention mask for text embeddings.
  • negative_prompt_embeds (torch.FloatTensor, optional) — Pre-generated negative text embeddings. For PixArt-Sigma this negative prompt should be "". If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.
  • negative_prompt_attention_mask (torch.FloatTensor, optional) — Pre-generated attention mask for negative text embeddings.
  • decode_timestep (float, defaults to 0.0) — The timestep at which generated video is decoded.
  • decode_noise_scale (float, defaults to None) — The interpolation factor between random noise and denoised latents at the decode timestep.
  • output_type (str, optional, defaults to "pil") — The output format of the generate image. Choose between PIL: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.ltx.LTX2PipelineOutput instead of a plain tuple.
  • attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.models.attention_processor.
  • callback_on_step_end (Callable, optional) — A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified by callback_on_step_end_tensor_inputs.
  • callback_on_step_end_tensor_inputs (List, optional) — The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the ._callback_tensor_inputs attribute of your pipeline class.
  • max_sequence_length (int, optional, defaults to 1024) — Maximum sequence length to use with the prompt.

Returns

~pipelines.ltx.LTX2PipelineOutput or tuple

If return_dict is True, ~pipelines.ltx.LTX2PipelineOutput is returned, otherwise a tuple is returned where the first element is a list with the generated images.

Function invoked when calling the pipeline for generation.

Examples:

>>> import torch
>>> from diffusers import LTX2Pipeline
>>> from diffusers.pipelines.ltx2.export_utils import encode_video
>>> from diffusers.utils import load_image

>>> pipe = LTX2ImageToVideoPipeline.from_pretrained("Lightricks/LTX-2", torch_dtype=torch.bfloat16)
>>> pipe.enable_model_cpu_offload()

>>> image = load_image(
...     "https://huggingface.co/datasets/a-r-r-o-w/tiny-meme-dataset-captioned/resolve/main/images/8.png"
... )
>>> prompt = "A young girl stands calmly in the foreground, looking directly at the camera, as a house fire rages in the background."
>>> negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"

>>> frame_rate = 24.0
>>> video = pipe(
...     image=image,
...     prompt=prompt,
...     negative_prompt=negative_prompt,
...     width=768,
...     height=512,
...     num_frames=121,
...     frame_rate=frame_rate,
...     num_inference_steps=40,
...     guidance_scale=4.0,
...     output_type="np",
...     return_dict=False,
... )
>>> video = (video * 255).round().astype("uint8")
>>> video = torch.from_numpy(video)

>>> encode_video(
...     video[0],
...     fps=frame_rate,
...     audio=audio[0].float().cpu(),
...     audio_sample_rate=pipe.vocoder.config.output_sampling_rate,  # should be 24000
...     output_path="video.mp4",
... )

encode_prompt

< >

( prompt: typing.Union[str, typing.List[str]] negative_prompt: typing.Union[str, typing.List[str], NoneType] = None do_classifier_free_guidance: bool = True num_videos_per_prompt: int = 1 prompt_embeds: typing.Optional[torch.Tensor] = None negative_prompt_embeds: typing.Optional[torch.Tensor] = None prompt_attention_mask: typing.Optional[torch.Tensor] = None negative_prompt_attention_mask: typing.Optional[torch.Tensor] = None max_sequence_length: int = 1024 scale_factor: int = 8 device: typing.Optional[torch.device] = None dtype: typing.Optional[torch.dtype] = None )

Parameters

  • prompt (str or List[str], optional) — prompt to be encoded
  • negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. If not defined, one has to pass negative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
  • do_classifier_free_guidance (bool, optional, defaults to True) — Whether to use classifier free guidance or not.
  • num_videos_per_prompt (int, optional, defaults to 1) — Number of videos that should be generated per prompt. torch device to place the resulting embeddings on
  • prompt_embeds (torch.Tensor, optional) — Pre-generated text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, text embeddings will be generated from prompt input argument.
  • negative_prompt_embeds (torch.Tensor, optional) — Pre-generated negative text embeddings. Can be used to easily tweak text inputs, e.g. prompt weighting. If not provided, negative_prompt_embeds will be generated from negative_prompt input argument.
  • device — (torch.device, optional): torch device
  • dtype — (torch.dtype, optional): torch dtype

Encodes the prompt into text encoder hidden states.

LTX2LatentUpsamplePipeline

class diffusers.LTX2LatentUpsamplePipeline

< >

( vae: AutoencoderKLLTX2Video latent_upsampler: LTX2LatentUpsamplerModel )

__call__

< >

( video: typing.Optional[typing.List[typing.Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, typing.List[PIL.Image.Image], typing.List[numpy.ndarray], typing.List[torch.Tensor]]]] = None height: int = 512 width: int = 768 num_frames: int = 121 spatial_patch_size: int = 1 temporal_patch_size: int = 1 latents: typing.Optional[torch.Tensor] = None latents_normalized: bool = False decode_timestep: typing.Union[float, typing.List[float]] = 0.0 decode_noise_scale: typing.Union[float, typing.List[float], NoneType] = None adain_factor: float = 0.0 tone_map_compression_ratio: float = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None output_type: typing.Optional[str] = 'pil' return_dict: bool = True ) ~pipelines.ltx.LTXPipelineOutput or tuple

Parameters

  • video (List[PipelineImageInput], optional) — The video to be upsampled (such as a LTX 2.0 first stage output). If not supplied, latents should be supplied.
  • height (int, optional, defaults to 512) — The height in pixels of the input video (not the generated video, which will have a larger resolution).
  • width (int, optional, defaults to 768) — The width in pixels of the input video (not the generated video, which will have a larger resolution).
  • num_frames (int, optional, defaults to 121) — The number of frames in the input video.
  • spatial_patch_size (int, optional, defaults to 1) — The spatial patch size of the video latents. Used when latents is supplied if unpacking is necessary.
  • temporal_patch_size (int, optional, defaults to 1) — The temporal patch size of the video latents. Used when latents is supplied if unpacking is necessary.
  • latents (torch.Tensor, optional) — Pre-generated video latents. This can be supplied in place of the video argument. Can either be a patch sequence of shape (batch_size, seq_len, hidden_dim) or a video latent of shape (batch_size, latent_channels, latent_frames, latent_height, latent_width).
  • latents_normalized (bool, optional, defaults to False) — If latents are supplied, whether the latents are normalized using the VAE latent mean and std. If True, the latents will be denormalized before being supplied to the latent upsampler.
  • decode_timestep (float, defaults to 0.0) — The timestep at which generated video is decoded.
  • decode_noise_scale (float, defaults to None) — The interpolation factor between random noise and denoised latents at the decode timestep.
  • adain_factor (float, optional, defaults to 0.0) — Adaptive Instance Normalization (AdaIN) blending factor between the upsampled and original latents. Should be in [-10.0, 10.0]; supplying 0.0 (the default) means that AdaIN is not performed.
  • tone_map_compression_ratio (float, optional, defaults to 0.0) — The compression strength for tone mapping, which will reduce the dynamic range of the latent values. This is useful for regularizing high-variance latents or for conditioning outputs during generation. Should be in [0, 1], where 0.0 (the default) means tone mapping is not applied and 1.0 corresponds to the full compression effect.
  • generator (torch.Generator or List[torch.Generator], optional) — One or a list of torch generator(s) to make generation deterministic.
  • output_type (str, optional, defaults to "pil") — The output format of the generate image. Choose between PIL: PIL.Image.Image or np.array.
  • return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.ltx.LTXPipelineOutput instead of a plain tuple.

Returns

~pipelines.ltx.LTXPipelineOutput or tuple

If return_dict is True, ~pipelines.ltx.LTXPipelineOutput is returned, otherwise a tuple is returned where the first element is the upsampled video.

Function invoked when calling the pipeline for generation.

Examples:

>>> import torch
>>> from diffusers import LTX2ImageToVideoPipeline, LTX2LatentUpsamplePipeline
>>> from diffusers.pipelines.ltx2.export_utils import encode_video
>>> from diffusers.pipelines.ltx2.latent_upsampler import LTX2LatentUpsamplerModel
>>> from diffusers.utils import load_image

>>> pipe = LTX2ImageToVideoPipeline.from_pretrained("Lightricks/LTX-2", torch_dtype=torch.bfloat16)
>>> pipe.enable_model_cpu_offload()

>>> image = load_image(
...     "https://huggingface.co/datasets/a-r-r-o-w/tiny-meme-dataset-captioned/resolve/main/images/8.png"
... )
>>> prompt = "A young girl stands calmly in the foreground, looking directly at the camera, as a house fire rages in the background."
>>> negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"

>>> frame_rate = 24.0
>>> video, audio = pipe(
...     image=image,
...     prompt=prompt,
...     negative_prompt=negative_prompt,
...     width=768,
...     height=512,
...     num_frames=121,
...     frame_rate=frame_rate,
...     num_inference_steps=40,
...     guidance_scale=4.0,
...     output_type="pil",
...     return_dict=False,
... )

>>> latent_upsampler = LTX2LatentUpsamplerModel.from_pretrained(
...     "Lightricks/LTX-2", subfolder="latent_upsampler", torch_dtype=torch.bfloat16
... )
>>> upsample_pipe = LTX2LatentUpsamplePipeline(vae=pipe.vae, latent_upsampler=latent_upsampler)
>>> upsample_pipe.vae.enable_tiling()
>>> upsample_pipe.to(device="cuda", dtype=torch.bfloat16)

>>> video = upsample_pipe(
...     video=video,
...     width=768,
...     height=512,
...     output_type="np",
...     return_dict=False,
... )[0]
>>> video = (video * 255).round().astype("uint8")
>>> video = torch.from_numpy(video)

>>> encode_video(
...     video[0],
...     fps=frame_rate,
...     audio=audio[0].float().cpu(),
...     audio_sample_rate=pipe.vocoder.config.output_sampling_rate,  # should be 24000
...     output_path="video.mp4",
... )

adain_filter_latent

< >

( latents: Tensor reference_latents: Tensor factor: float = 1.0 ) torch.Tensor

Parameters

  • latent (torch.Tensor) — Input latents to normalize
  • reference_latents (torch.Tensor) — The reference latents providing style statistics.
  • factor (float) — Blending factor between original and transformed latent. Range: -10.0 to 10.0, Default: 1.0

Returns

torch.Tensor

The transformed latent tensor

Applies Adaptive Instance Normalization (AdaIN) to a latent tensor based on statistics from a reference latent tensor.

tone_map_latents

< >

( latents: Tensor compression: float )

Parameters

  • latents — torch.Tensor Input latent tensor with arbitrary shape. Expected to be roughly in [-1, 1] or [0, 1] range.
  • compression — float Compression strength in the range [0, 1].
    • 0.0: No tone-mapping (identity transform)
    • 1.0: Full compression effect

Applies a non-linear tone-mapping function to latent values to reduce their dynamic range in a perceptually smooth way using a sigmoid-based compression.

This is useful for regularizing high-variance latents or for conditioning outputs during generation, especially when controlling dynamic behavior with a compression factor.

LTX2PipelineOutput

class diffusers.pipelines.ltx2.pipeline_output.LTX2PipelineOutput

< >

( frames: Tensor audio: Tensor )

Parameters

  • frames (torch.Tensor, np.ndarray, or List[List[PIL.Image.Image]]) — List of video outputs - It can be a nested list of length batch_size, with each sub-list containing denoised PIL image sequences of length num_frames. It can also be a NumPy array or Torch tensor of shape (batch_size, num_frames, channels, height, width).
  • audio (torch.Tensor, np.ndarray) — TODO

Output class for LTX pipelines.

Update on GitHub