3jSSKrSSKJr SSKrSSKrSSKrSSKJ r SSK J r J r JrJr SSKJrJr SSKJrJr SSKJr SS KJr SS KJr SS KJr SS KJrJ r J!r!J"r" SS K#J$r$ SSK%J&r& SSK'J(r( \ "5(a SSK)J*s J+r, Sr-OSr-\!R\"\/5r0\"5(aSSK1r1\!R\"\/5r0Sr2Sr3Sr4Sr5"SS\&\5r6g)N)Callable) functional) CLIPTextModel CLIPTokenizer"Qwen2_5_VLForConditionalGenerationQwen2VLProcessor)MultiPipelineCallbacksPipelineCallback)PipelineImageInputVaeImageProcessor)KandinskyLoraLoaderMixin) AutoencoderKL)Kandinsky5Transformer3DModel)FlowMatchEulerDiscreteScheduler)is_ftfy_availableis_torch_xla_availableloggingreplace_example_docstring) randn_tensor)DiffusionPipeline)KandinskyImagePipelineOutputTFa< Examples: ```python >>> import torch >>> from diffusers import Kandinsky5I2IPipeline >>> # Available models: >>> # kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers >>> # kandinskylab/Kandinsky-5.0-I2I-Lite-pretrain-Diffusers >>> model_id = "kandinskylab/Kandinsky-5.0-I2I-Lite-sft-Diffusers" >>> pipe = Kandinsky5I2IPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) >>> pipe = pipe.to("cuda") >>> prompt = "A cat and a dog baking a cake together in a kitchen." >>> output = pipe( ... prompt=prompt, ... negative_prompt="", ... height=1024, ... width=1024, ... num_inference_steps=50, ... guidance_scale=3.5, ... ).frames[0] ``` c[5(a[R"U5n[R"[R"U55nUR 5$)z Copied from https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/wan/pipeline_wan.py Clean text using ftfy if available and unescape HTML entities. )rftfyfix_texthtmlunescapestriptexts o/home/wildlama/miniconda3/lib/python3.13/site-packages/diffusers/pipelines/kandinsky5/pipeline_kandinsky_i2i.py basic_cleanr$Ws> }}T" ==t, -D ::<cV[R"SSU5nUR5nU$)z Copied from https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/wan/pipeline_wan.py Normalize whitespace in text by replacing multiple spaces with single space. z\s+ )resubr r!s r#whitespace_cleanr*cs& 66&#t $D ::text_encoder_2->transformer->vae)latentsprompt_embeds_qwenprompt_embeds_clipnegative_prompt_embeds_qwennegative_prompt_embeds_clip transformervae text_encoder tokenizertext_encoder_2 tokenizer_2 schedulerc >[TU]5 URUUUUUUUS9 SUlSUlSUl[ UR S9Ul/SQUlg)N)r5r6r7r8r9r:r;a=<|im_start|>system You are a promt engineer. Based on the provided source image (first image) and target image (second image), create an interesting text prompt that can be used together with the source image to create the target image:<|im_end|><|im_start|>user{}<|vision_start|><|image_pad|><|vision_end|><|im_end|>7)vae_scale_factor))r@))rBrA))rDrC))rFrE) super__init__register_modulesprompt_template prompt_template_encode_start_idxvae_scale_factor_spatialr image_processor resolutions) selfr5r6r7r8r9r:r; __class__s r#rHKandinsky5I2IPipeline.__init__sn  #%)#   `02-()%0$B_B_`wr%Nr@promptimagedevicemax_sequence_lengthdtypec *U=(d URnU=(d URRn[U[5(dU/nUVs/sH5ofR UR SS-UR SS-45PM7 nnUVs/sHopRRU5PM nnURU-n URUUSSSS9Sn U RS U :a[U5HupkXn XRR:HR5n XURR:gURS n URRXU - S - S5n[!U5S:dMU S[!U5*X'["R%S US U35 M URUUSU SSSS9R'U5nUR"S0UDSSS.D6SS SS2URS24nUSSS2URS24n[(R*"URS5SS9n[,R."USSS9R'[(R0S9nUR'U5U4$s snfs snf)aE Encode prompt using Qwen2.5-VL text encoder. This method processes the input prompt through the Qwen2.5-VL model to generate text embeddings suitable for image generation. Args: prompt list[str]: Input list of prompts image (PipelineImageInput): Input list of images to condition the generation on device (torch.device): Device to run encoding on max_sequence_length (int): Maximum sequence length for tokenization dtype (torch.dtype): Data type for embeddings Returns: tuple[torch.Tensor, torch.Tensor]: Text embeddings and cumulative sequence lengths rrrNptlongest)r"imagesvideosreturn_tensorspadding input_idsr zXThe following part of your input was truncated because `max_sequence_length` is set to z tokens: T)r"rZr[ max_length truncationr\r]) return_dictoutput_hidden_states hidden_statesattention_mask)dim)rr)valuerV)_execution_devicer7rV isinstancelistresizesizerJformatrKr8shape enumerateimage_token_idsumdecodelenloggerwarningtotorchcumsumFpadint32)rOrRrSrTrUrVip full_textsmax_allowed_lenuntruncated_idsr"tokensnum_image_tokens removed_textinputsembedsrf cu_seqlenss r#_encode_prompt_qwen)Kandinsky5I2IPipeline._encode_prompt_qwens014110**00%&&GEEJKU166!9>166!9>:;UK>DEf**11!4f E??BUU.. )     $ 6$Z0(+$*nn.K.K$K#P#P#R $..*G*G GHInInqst#~~44VRbJMNN/0 ,I1&   "V* ""  !%     !$"G"G"II K  01!T5Z5Z5\2\]\\."4"4Q"7Q? UU:vQ7:::M yy++[LEs