wi=ddlmZmZmZmZmZmZmZddlZddl m Z m Z ddl m Z ddlmZmZddlmZddlmZd d lmZmZd ZGd d eZdS))AnyCallableDictListOptionalTupleUnionN)CLIPTextModelWithProjection CLIPTokenizer)VaeImageProcessor) UVit2DModelVQModel)AmusedScheduler)replace_example_docstring)DiffusionPipelineImagePipelineOutputa{ Examples: ```py >>> import torch >>> from diffusers import AmusedPipeline >>> pipe = AmusedPipeline.from_pretrained("amused/amused-512", variant="fp16", torch_dtype=torch.float16) >>> pipe = pipe.to("cuda") >>> prompt = "a photo of an astronaut riding a horse on mars" >>> image = pipe(prompt).images[0] ``` c/eZdZUeed<eed<eed<eed<eed<e ed<dZ dedededede f fd Z e j ee d'deeeeefdeedeedededeeeeefdeedee jdee jdee jdee jdee jdee jded eeeee jgd fd!ed"eeeefd#ed$eeefd%eeeeefeeff(d&ZxZS)(AmusedPipelineimage_processorvqvae tokenizer text_encoder transformer schedulerz text_encoder->transformer->vqvaect||||||dt|jjjdz z|_t|jd|_ dS)N)rrrrrrF)vae_scale_factor do_normalize) super__init__register_moduleslenrconfigblock_out_channelsrr r)selfrrrrr __class__s z/root/.openclaw/workspace/chatterbox_venv_py311/lib/python3.11/site-packages/diffusers/pipelines/amused/pipeline_amused.pyr"zAmusedPipeline.__init__4s  %#    !"c$**;*N&O&ORS&S T0$BWfklllN $@rpilTrrrrpromptheightwidthnum_inference_stepsguidance_scalenegative_promptnum_images_per_prompt generatorlatents prompt_embedsencoder_hidden_statesnegative_prompt_embedsnegative_encoder_hidden_states return_dictcallbackcallback_stepscross_attention_kwargs"micro_conditioning_aesthetic_scoremicro_conditioning_crop_coord temperaturec ^ | | | | td| | | | td|| || tdt|tr|g}|t|}n | jd}||z}||jjj|jz}||jjj|jz}| m| |ddd|j j j |j }||dd }|j} |jd } | |d } | |d d } |d kr| |dgt|z}t|tr|g}| |ddd|j j j |j }||dd }|j} |jd } | |d } | |d d } t%j| | g} t%j| | g} t%j|||d|d |g|j | j}|d}||d krd|zn|d}|||jz||jzf}| 6t%j||jjjt$j|j } |j|||j t|jj||jjzz }||5}tA|jjD]\}}|d krt%j!| gdz}n| }|||| | |} |d kr#| "d\}!}"|!||"|!z zz} |j#| || |j$} |t|jjd z ks|d z|kr[|d z|jjzdkrE|%|/||zdkr&|tM|jdd z}#||#||  dddn #1swxYwY|dkr| }$n|j'jt$j(ko|j'jj)}%|%r|j'*|j'+| d|||jz||jz|j'jj,fj-.dd }$|j/0|$|}$|%r|j'1|2|s|$fStg|$S)an 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`. height (`int`, *optional*, defaults to `self.transformer.config.sample_size * self.vae_scale_factor`): The height in pixels of the generated image. width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`): The width in pixels of the generated image. num_inference_steps (`int`, *optional*, defaults to 16): 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. latents (`torch.IntTensor`, *optional*): Pre-generated tokens representing latent vectors in `self.vqvae`, to be used as inputs for image gneration. If not provided, the starting latents will be completely masked. 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://arxiv.org/abs/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://arxiv.org/abs/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 neitherzXpass either both `negatve_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_statesrg?)devicedtyper)rOrN)total) micro_condspooled_text_embr;rA) model_outputtimestepsampler8orderlatent)force_not_quantizeshape)4 ValueError isinstancestrr$rZrr% sample_sizerrmodel_max_length input_idsto_execution_devicer text_embeds hidden_statesrepeattorchconcattensorrO unsqueezeexpandfullr mask_token_idlong set_timesteps timestepsrW progress_bar enumeratecatchunkstep prev_sampleupdategetattrrfloat16 force_upcastfloatdecodelatent_channelsrVclipr postprocesshalfmaybe_free_model_hooksr)&r'r1r2r3r4r5r6r7r8r9r:r;r<r= output_typer>r?r@rArBrCrD batch_sizer`outputsrRrZnum_warmup_stepsrpirU model_inputrT uncond_logits cond_logitsstep_idxoutputneeds_upcastings& r)__call__zAmusedPipeline.__call__Hs~  %*?*G  !&;&Gfgg g " .3Q3Y " */M/Yj  N}4&:LQ^QjKLL L fc " " XF  VJJ&,Q/J"77 >%,84;PPF =$+7$:OOE  #$>: ' 4122 '' tZ^'__G#/M$+$9"$= !%,,-BAFF 5 < <=RTUWX Y Y C  %-"*')dS[[&8Oos338'6&7O NN##'(##~> + BBt566 ++I4^b+cc)0)<&181Fr1J.%;%B%BCXZ[%\%\ "-K-R-RShjkmn-o-o *!L*@-)PQQM$)L2PRg1h$i$i !l-a0-a02  )'-    "++A.. !((>C;O;OZU_acdd Vt'<\] ?jt~,:%*UYUkG $$%8+tG]^^^t~788;NQUQ_Qe;ee   %8  9 9 >\()ABB > > 8!C''"')WIM":":KK")K#// +$1*?+A 0   "C''1=1C1CA1F1F.M;#0>[S`E`3a#aL.--!-%"' .  DN455999U...AET^=Q3QUV3V3V '')))+N0Ba0G0G#$(K(K#K 8W===? > > > > > > > > > > > > > > > >D ( " "FF"j.%-?bDJDUDbO #   """Z&&#'d33T22J%5 '  TT!QZZ )55fkJJF " !!! ##%%% 9 "6***s$D-RR"%R")NNNr+r,NrNNNNNNr-TNrNr.r/r0) __name__ __module__ __qualname__r __annotations__rr r rrmodel_cpu_offload_seqr"rfno_gradrEXAMPLE_DOC_STRINGrr rr]intrz Generator IntTensorTensorboolrrrrr __classcell__)r(s@r)rr*s&&&& NNN---->mm!m2 m ! m # mmmmmm(U]__12237 $##% $;?/0/3-1048<9=AE GK;?239?>D-~+~+tCy#~./~+ ~+} ~+ ! ~+  ~+"%T#Y"78~+ (}~+EO,~+%/*~+  -~+ ( 5~+!) 6~+)1(>~+ !~+"8S#u|$rs EDDDDDDDDDDDDDDDDD CCCCCCCC000000********))))))......CCCCCCCC ^+^+^+^+^+&^+^+^+^+^+r*