+h;SSKJrJrJr SSKrSSKrSSKJr SSK J r J r SSK J r SSKJrJrJr SSKJr S S KJrJrJr S S KJr S S KJr S SKJr \"5(a SSKJs J r! Sr"OSr"\RF"\$5r%Sr&"SS\\5r'g))ListOptionalUnionN) CLIPTokenizer) AutoencoderKLUNet2DConditionModel) PNDMScheduler)is_torch_xla_availableloggingreplace_example_docstring) randn_tensor)DeprecatedPipelineMixinDiffusionPipelineImagePipelineOutput)BlipImageProcessor)Blip2QFormerModel)ContextCLIPTextModelTFah Examples: ```py >>> from diffusers.pipelines import BlipDiffusionPipeline >>> from diffusers.utils import load_image >>> import torch >>> blip_diffusion_pipe = BlipDiffusionPipeline.from_pretrained( ... "Salesforce/blipdiffusion", torch_dtype=torch.float16 ... ).to("cuda") >>> cond_subject = "dog" >>> tgt_subject = "dog" >>> text_prompt_input = "swimming underwater" >>> cond_image = load_image( ... "https://huggingface.co/datasets/ayushtues/blipdiffusion_images/resolve/main/dog.jpg" ... ) >>> guidance_scale = 7.5 >>> num_inference_steps = 25 >>> negative_prompt = "over-exposure, under-exposure, saturated, duplicate, out of frame, lowres, cropped, worst quality, low quality, jpeg artifacts, morbid, mutilated, out of frame, ugly, bad anatomy, bad proportions, deformed, blurry, duplicate" >>> output = blip_diffusion_pipe( ... text_prompt_input, ... cond_image, ... cond_subject, ... tgt_subject, ... guidance_scale=guidance_scale, ... num_inference_steps=num_inference_steps, ... neg_prompt=negative_prompt, ... height=512, ... width=512, ... ).images >>> output[0].save("image.png") ``` c!^\rSrSrSrSrSrS%S\S\S\ S\ S \ S \ S \ S \S \\S\\4U4SjjjrSrS&SjrS'SjrS'Sjr\R."5\"\5S(S\\S\R8R8S\\S\\S\\R<S\S\S\S\S\\\R@\\R@4S\\S\S \S!\\S"\!4S#jj55r"S$r#U=r$$))BlipDiffusionPipelineTaX Pipeline for Zero-Shot Subject Driven Generation using Blip Diffusion. This model inherits from [`DiffusionPipeline`]. Check the superclass documentation for the generic methods the library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.) Args: tokenizer ([`CLIPTokenizer`]): Tokenizer for the text encoder text_encoder ([`ContextCLIPTextModel`]): Text encoder to encode the text prompt vae ([`AutoencoderKL`]): VAE model to map the latents to the image unet ([`UNet2DConditionModel`]): Conditional U-Net architecture to denoise the image embedding. scheduler ([`PNDMScheduler`]): A scheduler to be used in combination with `unet` to generate image latents. qformer ([`Blip2QFormerModel`]): QFormer model to get multi-modal embeddings from the text and image. image_processor ([`BlipImageProcessor`]): Image Processor to preprocess and postprocess the image. ctx_begin_pos (int, `optional`, defaults to 2): Position of the context token in the text encoder. z0.33.1z qformer->text_encoder->unet->vae tokenizer text_encodervaeunet schedulerqformerimage_processor ctx_begin_posmeanstdc l>[T U]5 URUUUUUUUS9 URXU S9 g)N)rrrrrrr )r!r"r#)super__init__register_modulesregister_to_config) selfrrrrrrr r!r"r# __class__s t/home/james-whalen/.local/lib/python3.13/site-packages/diffusers/pipelines/blip_diffusion/pipeline_blip_diffusion.pyr&BlipDiffusionPipeline.__init__qsM  %+   mCPc"URXSS9$)NF) image_input text_input return_dict)r)r) input_image src_subjects r+get_query_embeddings*BlipDiffusionPipeline.get_query_embeddingss|| Y^|__r-c /n[X5HJupgSUSUR53nURSRU/[ X4-5-55 ML U$)Nza  z, )zipstripappendjoinint)r)prompts tgt_subjectsprompt_strength prompt_repsrvprompt tgt_subjects r+ _build_prompt#BlipDiffusionPipeline._build_prompts] #&w#= F+a '78F IIdii3/L+M MN O$>  r-c XX44n [U[5(a*[U5U:wa[S[U5SUS35eUc [ XXeS9nOUR XeS9nXR R-nU$)Nz/You have passed a list of generators of length z+, but requested an effective batch size of z@. Make sure the batch size matches the length of the generators.) generatordevicedtype)rHrI) isinstancelistlen ValueErrorrtorinit_noise_sigma) r) batch_size num_channelsheightwidthrIrHrGlatentsshapes r+prepare_latents%BlipDiffusionPipeline.prepare_latentss69 i & &3y>Z+GA#i.AQR&<'gi  ?"5fZGjjj>   * "V* "''* 223j@ ++&00'',    r-rBreference_imagesource_subject_categorytarget_subject_categoryrTguidance_scalerRrSnum_inference_stepsrG neg_promptr?r@ output_typer1c URnURRX RRURR SS9SnUR U5n[U[5(aU/n[U[5(aU/n[U[5(aU/n[U5nURUUU U S9nURX#5nURUUU5nUS:nU(aURRRRnUR!U /U-SUSS9nURUR"R U5SS 9S n[$R&"UU/5nS [UR(RR*5S - -nUR-UUR(RR.UU-UU-U UUR(R0US 9n0nUR2R4"U 40UD6 [7UR9UR2R:55HunnUS:nU(a[$R&"U/S -5OUnUR)UUUSSS9SnU(aUR=S 5unnUUUU- --nUR2R?UUU5Sn[@(dM[BRD"5 M URFRIXPRFRRJ- SS9S n URRMU US9n URO5 U(dU 4$[QU S9$)a/ Function invoked when calling the pipeline for generation. Args: prompt (`List[str]`): The prompt or prompts to guide the image generation. reference_image (`PIL.Image.Image`): The reference image to condition the generation on. source_subject_category (`List[str]`): The source subject category. target_subject_category (`List[str]`): The target subject category. 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 random sampling. guidance_scale (`float`, *optional*, defaults to 7.5): Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://huggingface.co/papers/2207.12598). `guidance_scale` is defined as `w` of equation 2. of [Imagen Paper](https://huggingface.co/papers/2205.11487). 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. height (`int`, *optional*, defaults to 512): The height of the generated image. width (`int`, *optional*, defaults to 512): The width of the generated image. 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. generator (`torch.Generator` or `List[torch.Generator]`, *optional*): One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make generation deterministic. neg_prompt (`str`, *optional*, defaults to ""): The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`). prompt_strength (`float`, *optional*, defaults to 1.0): The strength of the prompt. Specifies the number of times the prompt is repeated along with prompt_reps to amplify the prompt. prompt_reps (`int`, *optional*, defaults to 20): The number of times the prompt is repeated along with prompt_strength to amplify the prompt. output_type (`str`, *optional*, defaults to `"pil"`): The output format of the generate image. Choose between: `"pil"` (`PIL.Image.Image`), `"np"` (`np.array`) or `"pt"` (`torch.Tensor`). return_dict (`bool`, *optional*, defaults to `True`): Whether or not to return a [`~pipelines.ImagePipelineOutput`] instead of a plain tuple. Examples: Returns: [`~pipelines.ImagePipelineOutput`] or `tuple` rZ) image_mean image_stdr] pixel_values)r=r>r?r@?rY)r[rYr]N)r^r_rrr)rPrQrRrSrGrTrIrH)timestepencoder_hidden_statesdown_block_additional_residualsmid_block_additional_residualsample prev_sampleF)r1)rq)images))r`r preprocessrbr"r#rNrJstrrLrDr4rirrarcrr^torchcatrblock_out_channelsrV in_channelsrIr set_timesteps enumerate progress_bar timestepschunkstep XLA_AVAILABLExm mark_steprdecodescaling_factor postprocessmaybe_free_model_hooksr)!r)rBrkrlrmrTrnrRrSrorGrpr?r@rqr1rHrPrerhdo_classifier_free_guidancerY uncond_inputuncond_embeddingsscale_down_factorextra_set_kwargsitlatent_model_input noise_prednoise_pred_uncondnoise_pred_textimages! r+__call__BlipDiffusionPipeline.__call__swL''..99  (8(8DKKOOdh: *,,V4 fc " "XF -s 3 3'>&? # -s 3 3'>&? #[ ##0+# $  00Z ,,\66J&4s&:# &**55<<TTJ>> z)$%# *L !% 1 1&0033F;#!2!! $ii):O(LMO#dii&6&6&I&I"JQ"NO&&!))55..,,))//'   $$%8M '=XG9q=!9^e "&504.2 #  J+5?5E5Ea5H2!?.?UfCf1gg nn)) G } 5K8((//*H*H HV[\]^_$$00K0P ##%8O"%00r-)rNN)rv)N) Ng@r2NrvrpilT)%__name__ __module__ __qualname____firstlineno____doc___last_supported_versionmodel_cpu_offload_seqrrrr r rrr<rfloatr&r4rDrVrirno_gradr EXAMPLE_DOC_STRINGrPILImagerTensorr Generatorboolr__static_attributes__ __classcell__)r*s@r+rrTs2'> Q Q+Q Q # Q ! Q#Q,QQ5kQ%[QQ4`"4 ]]_12+/ ##%MQ$&!$%* !c1S c1c1"&c c1 "&c c1 %,,' c1c1c1c1!c1E%//43H"HIJc1SMc1c1c1c]c1 !c13c1r-r)(typingrrr PIL.Imagerr transformersrmodelsrr schedulersr utilsr r r utils.torch_utilsrpipeline_utilsrrrblip_image_processingrmodeling_blip2rmodeling_ctx_cliprtorch_xla.core.xla_modelcore xla_modelrr get_loggerrloggerrrrr-r+rs)( &9' .\\5-3))MM   H %%PU135FU1r-