3j{M vSSKrSSKrSSKJr SSKJrJr SSKrSSK r SSK r SSK J r JrJr SSKJrJr SSKJrJr SSKJrJr SS KJr SS KJr SS KJrJrJ r SS K!J"r" SS K#J$r$ SSK%J&r& SSK'J(r( SSK)J*r* SSK+J,r,J-r- \"5(a SSK.J/s J0r1 Sr2OSr2\Rf"\45r5Sr6\"SS55r7S*S\ RpS\ RrS-S\:4Sjjr;S+S\S,S"\>> import torch >>> from diffusers import LTX2ConditionPipeline >>> from diffusers.pipelines.ltx2.export_utils import encode_video >>> from diffusers.pipelines.ltx2.pipeline_ltx2_condition import LTX2VideoCondition >>> from diffusers.utils import load_image >>> pipe = LTX2ConditionPipeline.from_pretrained("Lightricks/LTX-2", torch_dtype=torch.bfloat16) >>> pipe.enable_model_cpu_offload() >>> first_image = load_image( ... "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_first_frame.png" ... ) >>> last_image = load_image( ... "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_last_frame.png" ... ) >>> first_cond = LTX2VideoCondition(frames=first_image, index=0, strength=1.0) >>> last_cond = LTX2VideoCondition(frames=last_image, index=-1, strength=1.0) >>> conditions = [first_cond, last_cond] >>> prompt = "CG animation style, a small blue bird takes off from the ground, flapping its wings." >>> negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted, static" >>> frame_rate = 24.0 >>> video = pipe( ... conditions=conditions, ... 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", ... ) ``` c\rSrSr%Sr\R R \\R R -\R-\ R-\ S'Sr \\ S'Sr\\ S'Srg ) LTX2VideoConditiondav Defines a single frame-conditioning item for LTX-2 Video - a single frame or a sequence of frames. Attributes: frames (`PIL.Image.Image` or `List[PIL.Image.Image]` or `np.ndarray` or `torch.Tensor`): The image (or video) to condition the video on. Accepts any type that can be handled by VideoProcessor.preprocess_video. index (`int`, defaults to `0`): The index at which the image or video will conditionally affect the video generation. strength (`float`, defaults to `1.0`): The strength of the conditioning effect. A value of `1.0` means the conditioning effect is fully applied. framesrindex?strengthN)__name__ __module__ __qualname____firstlineno____doc__PILImagelistnpndarraytorchTensor__annotations__r"intr$float__static_attributes__r%j/home/wildlama/miniconda3/lib/python3.13/site-packages/diffusers/pipelines/ltx2/pipeline_ltx2_condition.pyrrdsN  IIOOd399??3 3bjj @5<< OOE3NHer6rencoder_output generator sample_modec[US5(a!US:XaURRU5$[US5(a US:XaURR5$[US5(a UR$[ S5e)N latent_distsampleargmaxlatentsz3Could not access latents of provided encoder_output)hasattrr<r=moder?AttributeError)r8r9r:s r7retrieve_latentsrCys}~}--+2I))00;;  / /K84K))..00  + +%%%RSSr6 base_seq_len max_seq_len base_shift max_shiftc4XC- X!- - nX5U-- nX-U-nU$Nr%) image_seq_lenrDrErFrGmbmus r7calculate_shiftrNs3  K$>?A%%A  Q B Ir6num_inference_stepsdevice timestepssigmasc UbUb [S5eUbS[[R"UR5R R 55;nU(d[SURS35eUR"S X2S.UD6 URn[U5nX14$UbS[[R"UR5R R 55;nU(d[SURS35eUR"S XBS.UD6 URn[U5nX14$UR"U4S U0UD6 URnX14$) a Calls the scheduler's `set_timesteps` method and retrieves timesteps from the scheduler after the call. Handles custom timesteps. Any kwargs will be supplied to `scheduler.set_timesteps`. Args: scheduler (`SchedulerMixin`): The scheduler to get timesteps from. num_inference_steps (`int`): The number of diffusion steps used when generating samples with a pre-trained model. If used, `timesteps` must be `None`. device (`str` or `torch.device`, *optional*): The device to which the timesteps should be moved to. If `None`, the timesteps are not moved. timesteps (`list[int]`, *optional*): Custom timesteps used to override the timestep spacing strategy of the scheduler. If `timesteps` is passed, `num_inference_steps` and `sigmas` must be `None`. sigmas (`list[float]`, *optional*): Custom sigmas used to override the timestep spacing strategy of the scheduler. If `sigmas` is passed, `num_inference_steps` and `timesteps` must be `None`. Returns: `tuple[torch.Tensor, int]`: A tuple where the first element is the timestep schedule from the scheduler and the second element is the number of inference steps. zYOnly one of `timesteps` or `sigmas` can be passed. Please choose one to set custom valuesrQzThe current scheduler class zx's `set_timesteps` does not support custom timestep schedules. Please check whether you are using the correct scheduler.)rQrPrRzv's `set_timesteps` does not support custom sigmas schedules. Please check whether you are using the correct scheduler.)rRrPrPr%) ValueErrorsetinspect signature set_timesteps parameterskeys __class__rQlen) schedulerrOrPrQrRkwargsaccepts_timesteps accept_sigmass r7retrieve_timestepsras}>!3tuu'3w/@/@AXAX/Y/d/d/i/i/k+ll .y/B/B.CDab  M)MfM'' !)n  ))   C(9(9):Q:Q(R(](](b(b(d$ee .y/B/B.CD_`  GvGG'' !)n  ))  3MFMfM''  ))r6cUR[[SUR55SS9nUR[[SUR55SS9nXU- -nX%-SU- U--nU$)a Rescales `noise_cfg` tensor based on `guidance_rescale` to improve image quality and fix overexposure. Based on Section 3.4 from [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://huggingface.co/papers/2305.08891). Args: noise_cfg (`torch.Tensor`): The predicted noise tensor for the guided diffusion process. noise_pred_text (`torch.Tensor`): The predicted noise tensor for the text-guided diffusion process. guidance_rescale (`float`, *optional*, defaults to 0.0): A rescale factor applied to the noise predictions. Returns: noise_cfg (`torch.Tensor`): The rescaled noise prediction tensor. rT)dimkeepdim)stdr-rangendim) noise_cfgnoise_pred_textguidance_rescalestd_textstd_cfgnoise_pred_rescaleds r7rescale_noise_cfgrns{"""tE!_5I5I,J'KUY"ZHmmU1inn%= >mMG#''9: 6!>N:NR[9[[I r6cM^ ^\rSrSrSrSr/r/SQrS\S\ S\ S\ S \ \ -S \S \S \\-4U4S jjrSS\\\-S\S\S\S\R.S-S\R0S-4 SjjrSS\\\-S\\\-S-S\S\S\R6S-S\R6S-S\R6S-S\R6S-S\S\S\R.S-S\R0S-4SjjrSS jr\SS!\R6S"\S#\S$\R64S%jj5r\SS!\R6S&\S'\S(\S"\S#\S$\R64S)jj5r \SS!\R6S+\R6S,\R6S-\!S$\R64 S.jj5r"\SS!\R6S+\R6S,\R6S-\!S$\R64 S/jj5r#\SS!\R6S0\!\R6-S1\RHS-4S2jj5r%\SS!\R6S"\S-S#\S-S$\R64S3jj5r&\SS!\R6S4\S5\S"\S-S#\S-S$\R64 S6jj5r'\S!\R6S+\R6S,\R64S7j5r(\S!\R6S+\R6S,\R64S8j5r)S9\S:\S;\S$\4S<jr*SS@\+\\+-S-S'\S(\S&\S\R.S-S$\,\\R6\\!\\44 SAjjr-S!\R6SB\R6SC\\R6SD\\!SE\\SF\SG\S$\,\R6\R6\R644SHjr.SS@\+\\+-S-SI\SJ\S'\S(\S&\S0\!S\R0S-S\R.S-S1\RHS-S!\R6S-S$\,\R6\R6\R644SKjjr/SSI\SJ\SM\S5\S0\!S\R0S-S\R.S-S1\RHS-S!\R6S-S$\R64SNjjr0SSO\R6SP\R6SQ\S\1S-S$\R64 SRjjr2SSO\R6SP\R6SQ\S\1S-S$\R64 SSjjr3\4ST5r5\4SU5r6\4SV5r7\4SW5r8\4SX5r9\4SY5r:\4SZ5r;\4S[5r<\4S\5r=\4S]5r>\4S^5r?\4S_5r@\4S`5rA\4Sa5rB\4Sb5rC\R"5\E"\F5SSSS=S>S?ScSdSSSeSLS*SLSSSSSSSSSSSSSSSLSSfSgSSSS!/S4%S@\+\\+-S-S\\\-S\\\-S-S'\S(\S&\Sh\!Si\Sj\\!S-Sk\\!S-Sl\!Sm\!Sn\!So\!Sp\!S-Sq\!S-Sr\!S-Ss\!S-St\\S-S0\!S-S\S-S1\RH\\RH-S-S!\R6S-Su\R6S-S\R6S-S\R6S-S\R6S-S\R6S-Sv\!\\!-Sw\!\\!-S-Sx\Sy\Sz\S{\G\\14S-S|\H\\/S4S-S}\\S\4JS~jj55rISrJU=rK$)LTX2ConditionPipelinez Pipeline for video generation which allows image conditions to be inserted at arbitary parts of the video. Reference: https://github.com/Lightricks/LTX-Video TODO z>text_encoder->connectors->transformer->vae->audio_vae->vocoder)r? prompt_embedsnegative_prompt_embedsr]vae audio_vae text_encoder tokenizer connectors transformervocoderc >[T U]5 URUUUUUUUUS9 [USS5bURR OSUl[USS5bURROSUl[USS5bURROSUl [USS5bURROSUl [USS5b URRROSUl[US5b URRR"OSUl[USS5b URRR&OS Ul[USS5b URRR*OS Ul[/UR S S 9Ul[US S5bUR2R4UlgSUlg)N)rtrurvrwrxryrzr]rt ruryri>bilinear)vae_scale_factorresamplerw)super__init__register_modulesgetattrrtspatial_compression_ratiovae_spatial_compression_ratiotemporal_compression_ratiovae_temporal_compression_ratiorumel_compression_ratioaudio_vae_mel_compression_ratio$audio_vae_temporal_compression_ratioryconfig patch_sizetransformer_spatial_patch_size patch_size_ttransformer_temporal_patch_size sample_rateaudio_sampling_ratemel_hop_lengthaudio_hop_lengthrvideo_processorrwmodel_max_lengthtokenizer_max_length) selfr]rtrurvrwrxryrzr[s r7rLTX2ConditionPipeline.__init__s  %!#  3:$t2L2XDHH . .^` *4;43M3YDHH / /_` +5