+hWDSSKJrJrJrJrJrJrJr SSKrSSK J r J r SSK J r Jr SSKJrJr SSKJr SSKJrJr S S KJrJrJr \"5(a SSKJs Jr S rOS rS r "SS\\5r!g))AnyCallableDictListOptionalTupleUnionN)CLIPTextModelWithProjection CLIPTokenizer)PipelineImageInputVaeImageProcessor) UVit2DModelVQModel)AmusedScheduler)is_torch_xla_availablereplace_example_docstring)DeprecatedPipelineMixinDiffusionPipelineImagePipelineOutputTFa Examples: ```py >>> import torch >>> from diffusers import AmusedImg2ImgPipeline >>> from diffusers.utils import load_image >>> pipe = AmusedImg2ImgPipeline.from_pretrained( ... "amused/amused-512", variant="fp16", torch_dtype=torch.float16 ... ) >>> pipe = pipe.to("cuda") >>> prompt = "winter mountains" >>> input_image = ( ... load_image( ... "https://huggingface.co/datasets/diffusers/docs-images/resolve/main/open_muse/mountains.jpg" ... ) ... .resize((512, 512)) ... .convert("RGB") ... ) >>> image = pipe(prompt, input_image).images[0] ``` c-`^\rSrSr%Sr\\S'\\S'\\S'\ \S'\ \S'\ \S'S r S/r S\S\S\ S\ S\ 4 U4S jjr\R "5\"\5S!S \\\\\4S \S\S\S\S\\\\\4S\\S\\R4S\\R6S\\R6S\\R6S\\R6S\S\\\\\R6/S 4S\S\\\\4S\S\ \\4S\\\ \\4\\44&Sjj55r!S r"U=r#$)"AmusedImg2ImgPipeline<z0.33.1image_processorvqvae tokenizer text_encoder transformer schedulerz text_encoder->transformer->vqvaec >[TU]5 URUUUUUS9 [USS5(a/S[ UR R R5S- -OSUl[URSS9Ul g)N)rrrrr rrF)vae_scale_factor do_normalize) super__init__register_modulesgetattrlenrconfigblock_out_channelsr$rr)selfrrrrr __class__s l/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/pipelines/amused/pipeline_amused_img2img.pyr'AmusedImg2ImgPipeline.__init__Ls  %#  ELDRY[_D`D`A#djj''::;a? @fg  1$BWBWfklNpromptimagestrengthnum_inference_stepsguidance_scalenegative_promptnum_images_per_prompt generator prompt_embedsencoder_hidden_statesnegative_prompt_embedsnegative_encoder_hidden_states return_dictcallbackcallback_stepscross_attention_kwargs"micro_conditioning_aesthetic_scoremicro_conditioning_crop_coord temperaturec  U bU bU cU b [S5eU bU bU cU b [S5eUcU bUbU b [S5e[U[5(aU/nUb [U5nOU RSnUU-nU cvUR USSSUR R S 9RRUR5nURUSSS 9nURn URS n U RUS 5n U RUS S 5n US :aU cUcS/[U5-n[U[5(aU/nUR USSSUR R S 9RRUR5nURUSSS 9nURn URS n U RUS 5n U RUS S 5n [R"X/5n [R"X/5n UR R#U5nURS Sunn[R$"UUUSUS U/URU R&S9nUR)S5nUR+US :aSU-OUS5nUR,R/UUUR5 [1[UR,R25U-5n[UR,R25U- nUR4R&[R6:H=(a UR4R8R:nU(aUR4R=5 UR4R?URUR4R&URS95R@nURunnn n!UR4RCU5SSREUU U!5nUR,RGUUR,R2US - US9nURUS S 5nURIUS9n"[KU[UR,R255GHGn#UR,R2U#n$US :a[RL"U/S-5n%OUn%UROU%UU U US9n&US :aU&RQS5un'n(U'UU(U'- --n&UR,RSU&U$UUS9RTnU#[UR,R25S - :Xd U#S -UR,RV-S:Xa@U"RY5 Ub-U#U-S:Xa$U#[[UR,SS 5-n)U"U)U$U5 [\(dGM2[^R`"5 GMJ SSS5 U S:XaUn*OUR4RcUSUUURd-UURd-UR4R8Rf4S9RhRkSS 5n*UR RmU*U 5n*U(aUR4Ro5 URq5 U(dU*4$[sU*5$!,(df  N=f)a The call function to the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*): The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`. image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`): `Image`, numpy array or tensor representing an image batch to be used as the starting point. For both numpy array and pytorch tensor, the expected value range is between `[0, 1]` If it's a tensor or a list or tensors, the expected shape should be `(B, C, H, W)` or `(C, H, W)`. If it is a numpy array or a list of arrays, the expected shape should be `(B, H, W, C)` or `(H, W, C)` It can also accept image latents as `image`, but if passing latents directly it is not encoded again. strength (`float`, *optional*, defaults to 0.5): Indicates extent to transform the reference `image`. Must be between 0 and 1. `image` is used as a starting point and more noise is added the higher the `strength`. The number of denoising steps depends on the amount of noise initially added. When `strength` is 1, added noise is maximum and the denoising process runs for the full number of iterations specified in `num_inference_steps`. A value of 1 essentially ignores `image`. num_inference_steps (`int`, *optional*, defaults to 12): The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference. guidance_scale (`float`, *optional*, defaults to 10.0): A higher guidance scale value encourages the model to generate images closely linked to the text `prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`. negative_prompt (`str` or `List[str]`, *optional*): The prompt or prompts to guide what to not include in image generation. If not defined, you need to pass `negative_prompt_embeds` instead. Ignored when not using guidance (`guidance_scale < 1`). num_images_per_prompt (`int`, *optional*, defaults to 1): The number of images to generate per prompt. generator (`torch.Generator`, *optional*): A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation deterministic. prompt_embeds (`torch.Tensor`, *optional*): Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, text embeddings are generated from the `prompt` input argument. A single vector from the pooled and projected final hidden states. encoder_hidden_states (`torch.Tensor`, *optional*): Pre-generated penultimate hidden states from the text encoder providing additional text conditioning. negative_prompt_embeds (`torch.Tensor`, *optional*): Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument. negative_encoder_hidden_states (`torch.Tensor`, *optional*): Analogous to `encoder_hidden_states` for the positive prompt. output_type (`str`, *optional*, defaults to `"pil"`): The output format of the generated image. Choose between `PIL.Image` or `np.array`. return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] instead of a plain tuple. callback (`Callable`, *optional*): A function that calls every `callback_steps` steps during inference. The function is called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`. callback_steps (`int`, *optional*, defaults to 1): The frequency at which the `callback` function is called. If not specified, the callback is called at every step. cross_attention_kwargs (`dict`, *optional*): A kwargs dictionary that if specified is passed along to the [`AttentionProcessor`] as defined in [`self.processor`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py). micro_conditioning_aesthetic_score (`int`, *optional*, defaults to 6): The targeted aesthetic score according to the laion aesthetic classifier. See https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of https://huggingface.co/papers/2307.01952. micro_conditioning_crop_coord (`Tuple[int]`, *optional*, defaults to (0, 0)): The targeted height, width crop coordinates. See the micro-conditioning section of https://huggingface.co/papers/2307.01952. temperature (`Union[int, Tuple[int, int], List[int]]`, *optional*, defaults to (2, 0)): Configures the temperature scheduler on `self.scheduler` see `AmusedScheduler#set_timesteps`. Examples: Returns: [`~pipelines.pipeline_utils.ImagePipelineOutput`] or `tuple`: If `return_dict` is `True`, [`~pipelines.pipeline_utils.ImagePipelineOutput`] is returned, otherwise a `tuple` is returned where the first element is a list with the generated images. NzGpass either both `prompt_embeds` and `encoder_hidden_states` or neitherzYpass either both `negative_prompt_embeds` and `negative_encoder_hidden_states` or neitherz,pass only one of `prompt` or `prompt_embeds`rpt max_lengthT)return_tensorspadding truncationrG)r>output_hidden_statesr"g?)devicedtyper)rOrN)r9)total) micro_condspooled_text_embr;rA) model_outputtimestepsampler9orderlatent)force_not_quantizeshape): ValueError isinstancestrr*rZrmodel_max_length input_idsto_execution_devicer text_embeds hidden_statesrepeattorchconcatr preprocesstensorrO unsqueezeexpandr set_timestepsint timestepsrfloat16r+ force_upcastfloatencodelatentsquantizereshape add_noise progress_barrangecatrchunkstep prev_samplerWupdater) XLA_AVAILABLExm mark_stepdecoder$latent_channelsrVclip postprocesshalfmaybe_free_model_hooksr)+r-r2r3r4r5r6r7r8r9r:r;r<r= output_typer>r?r@rArBrCrD batch_sizer_outputsheightwidthrRstart_timestep_idxneeds_upcastingrr latents_bszchannelslatents_height latents_widthrvirU model_inputrT uncond_logits cond_logitsstep_idxoutputs+ r/__call__AmusedImg2ImgPipeline.__call__bsH  %*?*G  !&;&Gfg g " .3Q3Y " */M/Yk  N}4&:LQ^QjKL L fc " "XF  VJ&,,Q/J"77  #$>>:: ' i4112 '' tZ^'_G#//M$+$9$9"$= !%,,-BAF 5 < <=RTUWX Y C %-"*')dS[&8Oos33'6&7O NN##'(##~~>> + )BBt556 ++I4^b+c)0)<)<&181F1Fr1J.%;%B%BCXZ[%\ "-K-R-RShjkmn-o *!LL*@)PQM$)LL2P1h$i !$$//6 BC( ll-a0-a02  ))'--  "++A. !((>C;OZU_acd  $$%8+tG]G]^!#dnn&>&>"?("JK !9!9:=PP****emm;^ @Q@Q@^@^  JJ   **##EHH4::3C3CDLbLbH$cdll?F}}< X~}**%%g.q1!4<<[.Zgh..** T^^--.@1.DEQZ+ ..!61=   %8  9\-s4>>3K3K/LM>>33A6!C'"'))WIM":K")K#// +$1*?+A 0  "C'1=1C1CA1F.M;#0>[S`E`3a#aL..--!-%"' . + DNN44599q1uH\H\>\`a>a '')+N0Ba0G#$(K#K 8W= =LLNEN:J ( "FZZ&&#'d333T222JJ%%55 ' fTT!QZ ))55fkJF ! ##%9 "6**y: 9s9E[[ [!)rr$)NNg? g$@Nr"NNNNNpilTNr"N)rr)rr)$__name__ __module__ __qualname____firstlineno___last_supported_versionr__annotations__rr r rrmodel_cpu_offload_seq_exclude_from_cpu_offloadr'reno_gradrEXAMPLE_DOC_STRINGrr rr]r rprl GeneratorTensorboolrrrrr__static_attributes__ __classcell__)r.s@r/rr<sJ&&& N--> ") mm!m2 m ! m # m, ]]_1237$(#% $;?/0/3048<9=AE GK;?239?>D+G+tCy#~./G+"G+ G+ ! G+  G+"%T#Y"78G+ (}G+EOO,G+  -G+ ( 5G+!) 6G+)1(>G+G+ 8S#u||$rs^EDD CD*)F\\))MM2o+35Fo+r1