Diffusers documentation
LTX-Video
LTX-Video
LTX-Video is a diffusion transformer designed for fast and real-time generation of high-resolution videos from text and images. The main feature of LTX-Video is the Video-VAE. The Video-VAE has a higher pixel to latent compression ratio (1:192) which enables more efficient video data processing and faster generation speed. To support and prevent finer details from being lost during generation, the Video-VAE decoder performs the latent to pixel conversion and the last denoising step.
You can find all the original LTX-Video checkpoints under the Lightricks organization.
Click on the LTX-Video models in the right sidebar for more examples of other video generation tasks.
The example below demonstrates how to generate a video optimized for memory or inference speed.
Refer to the Reduce memory usage guide for more details about the various memory saving techniques.
The LTX-Video model below requires ~10GB of VRAM.
import torch
from diffusers import LTXPipeline, AutoModel
from diffusers.hooks import apply_group_offloading
from diffusers.utils import export_to_video
# fp8 layerwise weight-casting
transformer = AutoModel.from_pretrained(
"Lightricks/LTX-Video",
subfolder="transformer",
torch_dtype=torch.bfloat16
)
transformer.enable_layerwise_casting(
storage_dtype=torch.float8_e4m3fn, compute_dtype=torch.bfloat16
)
pipeline = LTXPipeline.from_pretrained("Lightricks/LTX-Video", transformer=transformer, torch_dtype=torch.bfloat16)
# group-offloading
onload_device = torch.device("cuda")
offload_device = torch.device("cpu")
pipeline.transformer.enable_group_offload(onload_device=onload_device, offload_device=offload_device, offload_type="leaf_level", use_stream=True)
apply_group_offloading(pipeline.text_encoder, onload_device=onload_device, offload_type="block_level", num_blocks_per_group=2)
apply_group_offloading(pipeline.vae, onload_device=onload_device, offload_type="leaf_level")
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"
video = pipeline(
prompt=prompt,
negative_prompt=negative_prompt,
width=768,
height=512,
num_frames=161,
decode_timestep=0.03,
decode_noise_scale=0.025,
num_inference_steps=50,
).frames[0]
export_to_video(video, "output.mp4", fps=24)
Notes
Refer to the following recommended settings for generation from the LTX-Video repository.
- The recommended dtype for the transformer, VAE, and text encoder is
torch.bfloat16
. The VAE and text encoder can also betorch.float32
ortorch.float16
. - For guidance-distilled variants of LTX-Video, set
guidance_scale
to1.0
. Theguidance_scale
for any other model should be set higher, like5.0
, for good generation quality. - For timestep-aware VAE variants (LTX-Video 0.9.1 and above), set
decode_timestep
to0.05
andimage_cond_noise_scale
to0.025
. - For variants that support interpolation between multiple conditioning images and videos (LTX-Video 0.9.5 and above), use similar images and videos for the best results. Divergence from the conditioning inputs may lead to abrupt transitionts in the generated video.
- The recommended dtype for the transformer, VAE, and text encoder is
LTX-Video 0.9.7 includes a spatial latent upscaler and a 13B parameter transformer. During inference, a low resolution video is quickly generated first and then upscaled and refined.
Show example code
import torch from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition from diffusers.utils import export_to_video, load_video pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-dev", torch_dtype=torch.bfloat16) pipeline_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", vae=pipeline.vae, torch_dtype=torch.bfloat16) pipeline.to("cuda") pipe_upsample.to("cuda") pipeline.vae.enable_tiling() def round_to_nearest_resolution_acceptable_by_vae(height, width): height = height - (height % pipeline.vae_temporal_compression_ratio) width = width - (width % pipeline.vae_temporal_compression_ratio) return height, width video = load_video( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cosmos/cosmos-video2world-input-vid.mp4" )[:21] # only use the first 21 frames as conditioning condition1 = LTXVideoCondition(video=video, frame_index=0) prompt = """ The video depicts a winding mountain road covered in snow, with a single vehicle traveling along it. The road is flanked by steep, rocky cliffs and sparse vegetation. The landscape is characterized by rugged terrain and a river visible in the distance. The scene captures the solitude and beauty of a winter drive through a mountainous region. """ negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted" expected_height, expected_width = 768, 1152 downscale_factor = 2 / 3 num_frames = 161 # 1. Generate video at smaller resolution # Text-only conditioning is also supported without the need to pass `conditions` downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor) downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width) latents = pipeline( conditions=[condition1], prompt=prompt, negative_prompt=negative_prompt, width=downscaled_width, height=downscaled_height, num_frames=num_frames, num_inference_steps=30, decode_timestep=0.05, decode_noise_scale=0.025, image_cond_noise_scale=0.0, guidance_scale=5.0, guidance_rescale=0.7, generator=torch.Generator().manual_seed(0), output_type="latent", ).frames # 2. Upscale generated video using latent upsampler with fewer inference steps # The available latent upsampler upscales the height/width by 2x upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2 upscaled_latents = pipe_upsample( latents=latents, output_type="latent" ).frames # 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended) video = pipeline( conditions=[condition1], prompt=prompt, negative_prompt=negative_prompt, width=upscaled_width, height=upscaled_height, num_frames=num_frames, denoise_strength=0.4, # Effectively, 4 inference steps out of 10 num_inference_steps=10, latents=upscaled_latents, decode_timestep=0.05, decode_noise_scale=0.025, image_cond_noise_scale=0.0, guidance_scale=5.0, guidance_rescale=0.7, generator=torch.Generator().manual_seed(0), output_type="pil", ).frames[0] # 4. Downscale the video to the expected resolution video = [frame.resize((expected_width, expected_height)) for frame in video] export_to_video(video, "output.mp4", fps=24)
LTX-Video 0.9.7 distilled model is guidance and timestep-distilled to speedup generation. It requires
guidance_scale
to be set to1.0
andnum_inference_steps
should be set between4
and10
for good generation quality. You should also use the following custom timesteps for the best results.- Base model inference to prepare for upscaling:
[1000, 993, 987, 981, 975, 909, 725, 0.03]
. - Upscaling:
[1000, 909, 725, 421, 0]
.
Show example code
import torch from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition from diffusers.utils import export_to_video, load_video pipeline = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-distilled", torch_dtype=torch.bfloat16) pipe_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", vae=pipeline.vae, torch_dtype=torch.bfloat16) pipeline.to("cuda") pipe_upsample.to("cuda") pipeline.vae.enable_tiling() def round_to_nearest_resolution_acceptable_by_vae(height, width): height = height - (height % pipeline.vae_temporal_compression_ratio) width = width - (width % pipeline.vae_temporal_compression_ratio) return height, width prompt = """ artistic anatomical 3d render, utlra quality, human half full male body with transparent skin revealing structure instead of organs, muscular, intricate creative patterns, monochromatic with backlighting, lightning mesh, scientific concept art, blending biology with botany, surreal and ethereal quality, unreal engine 5, ray tracing, ultra realistic, 16K UHD, rich details. camera zooms out in a rotating fashion """ negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted" expected_height, expected_width = 768, 1152 downscale_factor = 2 / 3 num_frames = 161 # 1. Generate video at smaller resolution downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor) downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width) latents = pipeline( prompt=prompt, negative_prompt=negative_prompt, width=downscaled_width, height=downscaled_height, num_frames=num_frames, timesteps=[1000, 993, 987, 981, 975, 909, 725, 0.03], decode_timestep=0.05, decode_noise_scale=0.025, image_cond_noise_scale=0.0, guidance_scale=1.0, guidance_rescale=0.7, generator=torch.Generator().manual_seed(0), output_type="latent", ).frames # 2. Upscale generated video using latent upsampler with fewer inference steps # The available latent upsampler upscales the height/width by 2x upscaled_height, upscaled_width = downscaled_height * 2, downscaled_width * 2 upscaled_latents = pipe_upsample( latents=latents, adain_factor=1.0, output_type="latent" ).frames # 3. Denoise the upscaled video with few steps to improve texture (optional, but recommended) video = pipeline( prompt=prompt, negative_prompt=negative_prompt, width=upscaled_width, height=upscaled_height, num_frames=num_frames, denoise_strength=0.999, # Effectively, 4 inference steps out of 5 timesteps=[1000, 909, 725, 421, 0], latents=upscaled_latents, decode_timestep=0.05, decode_noise_scale=0.025, image_cond_noise_scale=0.0, guidance_scale=1.0, guidance_rescale=0.7, generator=torch.Generator().manual_seed(0), output_type="pil", ).frames[0] # 4. Downscale the video to the expected resolution video = [frame.resize((expected_width, expected_height)) for frame in video] export_to_video(video, "output.mp4", fps=24)
- Base model inference to prepare for upscaling:
LTX-Video supports LoRAs with load_lora_weights().
Show example code
import torch from diffusers import LTXConditionPipeline from diffusers.utils import export_to_video, load_image pipeline = LTXConditionPipeline.from_pretrained( "Lightricks/LTX-Video-0.9.5", torch_dtype=torch.bfloat16 ) pipeline.load_lora_weights("Lightricks/LTX-Video-Cakeify-LoRA", adapter_name="cakeify") pipeline.set_adapters("cakeify") # use "CAKEIFY" to trigger the LoRA prompt = "CAKEIFY a person using a knife to cut a cake shaped like a Pikachu plushie" image = load_image("https://huggingface.co/Lightricks/LTX-Video-Cakeify-LoRA/resolve/main/assets/images/pikachu.png") video = pipeline( prompt=prompt, image=image, width=576, height=576, num_frames=161, decode_timestep=0.03, decode_noise_scale=0.025, num_inference_steps=50, ).frames[0] export_to_video(video, "output.mp4", fps=26)
LTX-Video supports loading from single files, such as GGUF checkpoints, with loaders.FromOriginalModelMixin.from_single_file() or loaders.FromSingleFileMixin.from_single_file().
Show example code
import torch from diffusers.utils import export_to_video from diffusers import LTXPipeline, AutoModel, GGUFQuantizationConfig transformer = AutoModel.from_single_file( "https://huggingface.co/city96/LTX-Video-gguf/blob/main/ltx-video-2b-v0.9-Q3_K_S.gguf" quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16), torch_dtype=torch.bfloat16 ) pipeline = LTXPipeline.from_pretrained( "Lightricks/LTX-Video", transformer=transformer, torch_dtype=torch.bfloat16 )
LTXPipeline
class diffusers.LTXPipeline
< source >( scheduler: FlowMatchEulerDiscreteScheduler vae: AutoencoderKLLTXVideo text_encoder: T5EncoderModel tokenizer: T5TokenizerFast transformer: LTXVideoTransformer3DModel )
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.
Pipeline for text-to-video generation.
Reference: https://github.com/Lightricks/LTX-Video
__call__
< source >( prompt: typing.Union[str, typing.List[str]] = None negative_prompt: typing.Union[str, typing.List[str], NoneType] = None height: int = 512 width: int = 704 num_frames: int = 161 frame_rate: int = 25 num_inference_steps: int = 50 timesteps: typing.List[int] = None guidance_scale: float = 3 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 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 = 128 ) → ~pipelines.ltx.LTXPipelineOutput
or tuple
Parameters
- prompt (
str
orList[str]
, optional) — The prompt or prompts to guide the image generation. If not defined, one has to passprompt_embeds
. instead. - height (
int
, defaults to512
) — The height in pixels of the generated image. This is set to 480 by default for the best results. - width (
int
, defaults to704
) — The width in pixels of the generated image. This is set to 848 by default for the best results. - num_frames (
int
, defaults to161
) — The number of video frames to generate - num_inference_steps (
int
, optional, defaults to 50) — 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 atimesteps
argument in theirset_timesteps
method. If not defined, the default behavior whennum_inference_steps
is passed will be used. Must be in descending order. - guidance_scale (
float
, defaults to3
) — Guidance scale as defined in Classifier-Free Diffusion Guidance.guidance_scale
is defined asw
of equation 2. of Imagen Paper. Guidance scale is enabled by settingguidance_scale > 1
. Higher guidance scale encourages to generate images that are closely linked to the textprompt
, 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 Flawedguidance_scale
is defined asφ
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
orList[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 image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied randomgenerator
. - 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 fromprompt
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 fromnegative_prompt
input argument. - negative_prompt_attention_mask (
torch.FloatTensor
, optional) — Pre-generated attention mask for negative text embeddings. - decode_timestep (
float
, defaults to0.0
) — The timestep at which generated video is decoded. - decode_noise_scale (
float
, defaults toNone
) — 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
ornp.array
. - return_dict (
bool
, optional, defaults toTrue
) — Whether or not to return a~pipelines.ltx.LTXPipelineOutput
instead of a plain tuple. - attention_kwargs (
dict
, optional) — A kwargs dictionary that if specified is passed along to theAttentionProcessor
as defined underself.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 bycallback_on_step_end_tensor_inputs
. - callback_on_step_end_tensor_inputs (
List
, optional) — The list of tensor inputs for thecallback_on_step_end
function. The tensors specified in the list will be passed ascallback_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
defaults to128
) — Maximum sequence length to use with theprompt
.
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 a list with the generated images.
Function invoked when calling the pipeline for generation.
Examples:
>>> import torch
>>> from diffusers import LTXPipeline
>>> from diffusers.utils import export_to_video
>>> pipe = LTXPipeline.from_pretrained("Lightricks/LTX-Video", torch_dtype=torch.bfloat16)
>>> pipe.to("cuda")
>>> 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"
>>> video = pipe(
... prompt=prompt,
... negative_prompt=negative_prompt,
... width=704,
... height=480,
... num_frames=161,
... num_inference_steps=50,
... ).frames[0]
>>> export_to_video(video, "output.mp4", fps=24)
encode_prompt
< source >( 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 = 128 device: typing.Optional[torch.device] = None dtype: typing.Optional[torch.dtype] = None )
Parameters
- prompt (
str
orList[str]
, optional) — prompt to be encoded - negative_prompt (
str
orList[str]
, optional) — The prompt or prompts not to guide the image generation. If not defined, one has to passnegative_prompt_embeds
instead. Ignored when not using guidance (i.e., ignored ifguidance_scale
is less than1
). - do_classifier_free_guidance (
bool
, optional, defaults toTrue
) — 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 fromprompt
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 fromnegative_prompt
input argument. - device — (
torch.device
, optional): torch device - dtype — (
torch.dtype
, optional): torch dtype
Encodes the prompt into text encoder hidden states.
LTXImageToVideoPipeline
class diffusers.LTXImageToVideoPipeline
< source >( scheduler: FlowMatchEulerDiscreteScheduler vae: AutoencoderKLLTXVideo text_encoder: T5EncoderModel tokenizer: T5TokenizerFast transformer: LTXVideoTransformer3DModel )
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.
Pipeline for image-to-video generation.
Reference: https://github.com/Lightricks/LTX-Video
__call__
< source >( 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 = 704 num_frames: int = 161 frame_rate: int = 25 num_inference_steps: int = 50 timesteps: typing.List[int] = None guidance_scale: float = 3 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 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 = 128 ) → ~pipelines.ltx.LTXPipelineOutput
or tuple
Parameters
- image (
PipelineImageInput
) — The input image to condition the generation on. Must be an image, a list of images or atorch.Tensor
. - prompt (
str
orList[str]
, optional) — The prompt or prompts to guide the image generation. If not defined, one has to passprompt_embeds
. instead. - height (
int
, defaults to512
) — The height in pixels of the generated image. This is set to 480 by default for the best results. - width (
int
, defaults to704
) — The width in pixels of the generated image. This is set to 848 by default for the best results. - num_frames (
int
, defaults to161
) — The number of video frames to generate - num_inference_steps (
int
, optional, defaults to 50) — 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 atimesteps
argument in theirset_timesteps
method. If not defined, the default behavior whennum_inference_steps
is passed will be used. Must be in descending order. - guidance_scale (
float
, defaults to3
) — Guidance scale as defined in Classifier-Free Diffusion Guidance.guidance_scale
is defined asw
of equation 2. of Imagen Paper. Guidance scale is enabled by settingguidance_scale > 1
. Higher guidance scale encourages to generate images that are closely linked to the textprompt
, 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 Flawedguidance_scale
is defined asφ
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
orList[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 image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied randomgenerator
. - 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 fromprompt
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 fromnegative_prompt
input argument. - negative_prompt_attention_mask (
torch.FloatTensor
, optional) — Pre-generated attention mask for negative text embeddings. - decode_timestep (
float
, defaults to0.0
) — The timestep at which generated video is decoded. - decode_noise_scale (
float
, defaults toNone
) — 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
ornp.array
. - return_dict (
bool
, optional, defaults toTrue
) — Whether or not to return a~pipelines.ltx.LTXPipelineOutput
instead of a plain tuple. - attention_kwargs (
dict
, optional) — A kwargs dictionary that if specified is passed along to theAttentionProcessor
as defined underself.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 bycallback_on_step_end_tensor_inputs
. - callback_on_step_end_tensor_inputs (
List
, optional) — The list of tensor inputs for thecallback_on_step_end
function. The tensors specified in the list will be passed ascallback_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
defaults to128
) — Maximum sequence length to use with theprompt
.
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 a list with the generated images.
Function invoked when calling the pipeline for generation.
Examples:
>>> import torch
>>> from diffusers import LTXImageToVideoPipeline
>>> from diffusers.utils import export_to_video, load_image
>>> pipe = LTXImageToVideoPipeline.from_pretrained("Lightricks/LTX-Video", torch_dtype=torch.bfloat16)
>>> pipe.to("cuda")
>>> 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. Flames engulf the structure, with smoke billowing into the air. Firefighters in protective gear rush to the scene, a fire truck labeled '38' visible behind them. The girl's neutral expression contrasts sharply with the chaos of the fire, creating a poignant and emotionally charged scene."
>>> negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
>>> video = pipe(
... image=image,
... prompt=prompt,
... negative_prompt=negative_prompt,
... width=704,
... height=480,
... num_frames=161,
... num_inference_steps=50,
... ).frames[0]
>>> export_to_video(video, "output.mp4", fps=24)
encode_prompt
< source >( 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 = 128 device: typing.Optional[torch.device] = None dtype: typing.Optional[torch.dtype] = None )
Parameters
- prompt (
str
orList[str]
, optional) — prompt to be encoded - negative_prompt (
str
orList[str]
, optional) — The prompt or prompts not to guide the image generation. If not defined, one has to passnegative_prompt_embeds
instead. Ignored when not using guidance (i.e., ignored ifguidance_scale
is less than1
). - do_classifier_free_guidance (
bool
, optional, defaults toTrue
) — 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 fromprompt
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 fromnegative_prompt
input argument. - device — (
torch.device
, optional): torch device - dtype — (
torch.dtype
, optional): torch dtype
Encodes the prompt into text encoder hidden states.
LTXConditionPipeline
class diffusers.LTXConditionPipeline
< source >( scheduler: FlowMatchEulerDiscreteScheduler vae: AutoencoderKLLTXVideo text_encoder: T5EncoderModel tokenizer: T5TokenizerFast transformer: LTXVideoTransformer3DModel )
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.
Pipeline for text/image/video-to-video generation.
Reference: https://github.com/Lightricks/LTX-Video
__call__
< source >( conditions: typing.Union[diffusers.pipelines.ltx.pipeline_ltx_condition.LTXVideoCondition, typing.List[diffusers.pipelines.ltx.pipeline_ltx_condition.LTXVideoCondition]] = None image: typing.Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, typing.List[PIL.Image.Image], typing.List[numpy.ndarray], typing.List[torch.Tensor], 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 video: 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 frame_index: typing.Union[int, typing.List[int]] = 0 strength: typing.Union[float, typing.List[float]] = 1.0 denoise_strength: float = 1.0 prompt: typing.Union[str, typing.List[str]] = None negative_prompt: typing.Union[str, typing.List[str], NoneType] = None height: int = 512 width: int = 704 num_frames: int = 161 frame_rate: int = 25 num_inference_steps: int = 50 timesteps: typing.List[int] = None guidance_scale: float = 3 guidance_rescale: float = 0.0 image_cond_noise_scale: float = 0.15 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 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 = 256 ) → ~pipelines.ltx.LTXPipelineOutput
or tuple
Parameters
- conditions (
List[LTXVideoCondition], *optional*
) — The list of frame-conditioning items for the video generation.If not provided, conditions will be created usingimage
,video
,frame_index
andstrength
. - image (
PipelineImageInput
orList[PipelineImageInput]
, optional) — The image or images to condition the video generation. If not provided, one has to passvideo
orconditions
. - video (
List[PipelineImageInput]
, optional) — The video to condition the video generation. If not provided, one has to passimage
orconditions
. - frame_index (
int
orList[int]
, optional) — The frame index or frame indices at which the image or video will conditionally effect the video generation. If not provided, one has to passconditions
. - strength (
float
orList[float]
, optional) — The strength or strengths of the conditioning effect. If not provided, one has to passconditions
. - denoise_strength (
float
, defaults to1.0
) — The strength of the noise added to the latents for editing. Higher strength leads to more noise added to the latents, therefore leading to more differences between original video and generated video. This is useful for video-to-video editing. - prompt (
str
orList[str]
, optional) — The prompt or prompts to guide the image generation. If not defined, one has to passprompt_embeds
. instead. - height (
int
, defaults to512
) — The height in pixels of the generated image. This is set to 480 by default for the best results. - width (
int
, defaults to704
) — The width in pixels of the generated image. This is set to 848 by default for the best results. - num_frames (
int
, defaults to161
) — The number of video frames to generate - num_inference_steps (
int
, optional, defaults to 50) — 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 atimesteps
argument in theirset_timesteps
method. If not defined, the default behavior whennum_inference_steps
is passed will be used. Must be in descending order. - guidance_scale (
float
, defaults to3
) — Guidance scale as defined in Classifier-Free Diffusion Guidance.guidance_scale
is defined asw
of equation 2. of Imagen Paper. Guidance scale is enabled by settingguidance_scale > 1
. Higher guidance scale encourages to generate images that are closely linked to the textprompt
, 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 Flawedguidance_scale
is defined asφ
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
orList[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 image generation. Can be used to tweak the same generation with different prompts. If not provided, a latents tensor will ge generated by sampling using the supplied randomgenerator
. - 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 fromprompt
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 fromnegative_prompt
input argument. - negative_prompt_attention_mask (
torch.FloatTensor
, optional) — Pre-generated attention mask for negative text embeddings. - decode_timestep (
float
, defaults to0.0
) — The timestep at which generated video is decoded. - decode_noise_scale (
float
, defaults toNone
) — 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
ornp.array
. - return_dict (
bool
, optional, defaults toTrue
) — Whether or not to return a~pipelines.ltx.LTXPipelineOutput
instead of a plain tuple. - attention_kwargs (
dict
, optional) — A kwargs dictionary that if specified is passed along to theAttentionProcessor
as defined underself.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 bycallback_on_step_end_tensor_inputs
. - callback_on_step_end_tensor_inputs (
List
, optional) — The list of tensor inputs for thecallback_on_step_end
function. The tensors specified in the list will be passed ascallback_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
defaults to128
) — Maximum sequence length to use with theprompt
.
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 a list with the generated images.
Function invoked when calling the pipeline for generation.
Examples:
>>> import torch
>>> from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXConditionPipeline, LTXVideoCondition
>>> from diffusers.utils import export_to_video, load_video, load_image
>>> pipe = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.5", torch_dtype=torch.bfloat16)
>>> pipe.to("cuda")
>>> # Load input image and video
>>> video = load_video(
... "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cosmos/cosmos-video2world-input-vid.mp4"
... )
>>> image = load_image(
... "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cosmos/cosmos-video2world-input.jpg"
... )
>>> # Create conditioning objects
>>> condition1 = LTXVideoCondition(
... image=image,
... frame_index=0,
... )
>>> condition2 = LTXVideoCondition(
... video=video,
... frame_index=80,
... )
>>> prompt = "The video depicts a long, straight highway stretching into the distance, flanked by metal guardrails. The road is divided into multiple lanes, with a few vehicles visible in the far distance. The surrounding landscape features dry, grassy fields on one side and rolling hills on the other. The sky is mostly clear with a few scattered clouds, suggesting a bright, sunny day. And then the camera switch to a winding mountain road covered in snow, with a single vehicle traveling along it. The road is flanked by steep, rocky cliffs and sparse vegetation. The landscape is characterized by rugged terrain and a river visible in the distance. The scene captures the solitude and beauty of a winter drive through a mountainous region."
>>> negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
>>> # Generate video
>>> generator = torch.Generator("cuda").manual_seed(0)
>>> # Text-only conditioning is also supported without the need to pass `conditions`
>>> video = pipe(
... conditions=[condition1, condition2],
... prompt=prompt,
... negative_prompt=negative_prompt,
... width=768,
... height=512,
... num_frames=161,
... num_inference_steps=40,
... generator=generator,
... ).frames[0]
>>> export_to_video(video, "output.mp4", fps=24)
add_noise_to_image_conditioning_latents
< source >( t: float init_latents: Tensor latents: Tensor noise_scale: float conditioning_mask: Tensor generator eps = 1e-06 )
Add timestep-dependent noise to the hard-conditioning latents. This helps with motion continuity, especially when conditioned on a single frame.
encode_prompt
< source >( 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 = 256 device: typing.Optional[torch.device] = None dtype: typing.Optional[torch.dtype] = None )
Parameters
- prompt (
str
orList[str]
, optional) — prompt to be encoded - negative_prompt (
str
orList[str]
, optional) — The prompt or prompts not to guide the image generation. If not defined, one has to passnegative_prompt_embeds
instead. Ignored when not using guidance (i.e., ignored ifguidance_scale
is less than1
). - do_classifier_free_guidance (
bool
, optional, defaults toTrue
) — 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 fromprompt
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 fromnegative_prompt
input argument. - device — (
torch.device
, optional): torch device - dtype — (
torch.dtype
, optional): torch dtype
Encodes the prompt into text encoder hidden states.
trim_conditioning_sequence
< source >( start_frame: int sequence_num_frames: int target_num_frames: int ) → int
Trim a conditioning sequence to the allowed number of frames.
LTXLatentUpsamplePipeline
class diffusers.LTXLatentUpsamplePipeline
< source >( vae: AutoencoderKLLTXVideo latent_upsampler: LTXLatentUpsamplerModel )
__call__
< source >( 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 = 704 latents: 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 adain_factor: 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 )
adain_filter_latent
< source >( 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.
Disable sliced VAE decoding. If enable_vae_slicing
was previously enabled, this method will go back to
computing decoding in one step.
Disable tiled VAE decoding. If enable_vae_tiling
was previously enabled, this method will go back to
computing decoding in one step.
Enable sliced VAE decoding. When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several steps. This is useful to save some memory and allow larger batch sizes.
Enable tiled VAE decoding. When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in several steps. This is useful for saving a large amount of memory and to allow processing larger images.
LTXPipelineOutput
class diffusers.pipelines.ltx.pipeline_output.LTXPipelineOutput
< source >( frames: Tensor )
Parameters
- frames (
torch.Tensor
,np.ndarray
, or List[List[PIL.Image.Image]]) — List of video outputs - It can be a nested list of lengthbatch_size,
with each sub-list containing denoised PIL image sequences of lengthnum_frames.
It can also be a NumPy array or Torch tensor of shape(batch_size, num_frames, channels, height, width)
.
Output class for LTX pipelines.