From 2630fe360831708d712ef760bb05b18b329bb538 Mon Sep 17 00:00:00 2001 From: Ryan Dick Date: Fri, 8 Sep 2023 16:25:34 -0400 Subject: [PATCH] Remove unused ip_adapter/utils.py file. --- invokeai/backend/ip_adapter/utils.py | 366 --------------------------- 1 file changed, 366 deletions(-) delete mode 100644 invokeai/backend/ip_adapter/utils.py diff --git a/invokeai/backend/ip_adapter/utils.py b/invokeai/backend/ip_adapter/utils.py deleted file mode 100644 index b500fd2570..0000000000 --- a/invokeai/backend/ip_adapter/utils.py +++ /dev/null @@ -1,366 +0,0 @@ -# copied from https://github.com/tencent-ailab/IP-Adapter (Apache License 2.0) -# and modified as needed - -from typing import Any, Callable, Dict, List, Optional, Union - -import numpy as np -import PIL.Image -import torch -import torch.nn.functional as F -from diffusers.models import ControlNetModel -from diffusers.pipelines.controlnet.multicontrolnet import MultiControlNetModel -from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput -from diffusers.utils import is_compiled_module - - -def is_torch2_available(): - return hasattr(F, "scaled_dot_product_attention") - - -@torch.no_grad() -def generate( - self, - prompt: Union[str, List[str], None] = None, - image: Union[ - torch.FloatTensor, - PIL.Image.Image, - np.ndarray, - List[torch.FloatTensor], - List[PIL.Image.Image], - List[np.ndarray], - None, - ] = None, - height: Optional[int] = None, - width: Optional[int] = None, - num_inference_steps: int = 50, - guidance_scale: float = 7.5, - negative_prompt: Optional[Union[str, List[str]]] = None, - num_images_per_prompt: Optional[int] = 1, - eta: float = 0.0, - generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None, - latents: Optional[torch.FloatTensor] = None, - prompt_embeds: Optional[torch.FloatTensor] = None, - negative_prompt_embeds: Optional[torch.FloatTensor] = None, - output_type: Optional[str] = "pil", - return_dict: bool = True, - callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None, - callback_steps: int = 1, - cross_attention_kwargs: Optional[Dict[str, Any]] = None, - controlnet_conditioning_scale: Union[float, List[float]] = 1.0, - guess_mode: bool = False, - control_guidance_start: Union[float, List[float]] = 0.0, - control_guidance_end: Union[float, List[float]] = 1.0, -): - r""" - Function invoked when calling the pipeline for generation. - - Args: - prompt (`str` or `List[str]`, *optional*): - The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`. - instead. - image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, - `List[np.ndarray]`,: - `List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`): - The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If - the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can - also be accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If - height and/or width are passed, `image` is resized according to them. If multiple ControlNets are - specified in init, images must be passed as a list such that each element of the list can be correctly - batched for input to a single controlnet. - height (`int`, *optional*, defaults to self.unet.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 50): - 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 7.5): - Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598). - `guidance_scale` is defined as `w` of equation 2. of [Imagen - Paper](https://arxiv.org/pdf/2205.11487.pdf). 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. - negative_prompt (`str` or `List[str]`, *optional*): - The prompt or prompts not to guide the image generation. If not defined, one has to pass - `negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is - less than `1`). - num_images_per_prompt (`int`, *optional*, defaults to 1): - The number of images to generate per prompt. - eta (`float`, *optional*, defaults to 0.0): - Corresponds to parameter eta (η) in the DDIM paper: https://arxiv.org/abs/2010.02502. Only applies to - [`schedulers.DDIMScheduler`], will be ignored for others. - 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. - latents (`torch.FloatTensor`, *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 sampling using the supplied random `generator`. - prompt_embeds (`torch.FloatTensor`, *optional*): - Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not - provided, text embeddings will be generated from `prompt` input argument. - negative_prompt_embeds (`torch.FloatTensor`, *optional*): - Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt - weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input - argument. - output_type (`str`, *optional*, defaults to `"pil"`): - The output format of the generate image. Choose between - [PIL](https://pillow.readthedocs.io/en/stable/): `PIL.Image.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 will be called every `callback_steps` steps during inference. The function will be - called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`. - callback_steps (`int`, *optional*, defaults to 1): - The frequency at which the `callback` function will be called. If not specified, the callback will be - called at every step. - cross_attention_kwargs (`dict`, *optional*): - A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under - `self.processor` in - [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py). - controlnet_conditioning_scale (`float` or `List[float]`, *optional*, defaults to 1.0): - The outputs of the controlnet are multiplied by `controlnet_conditioning_scale` before they are added - to the residual in the original unet. If multiple ControlNets are specified in init, you can set the - corresponding scale as a list. - guess_mode (`bool`, *optional*, defaults to `False`): - In this mode, the ControlNet encoder will try best to recognize the content of the input image even if - you remove all prompts. The `guidance_scale` between 3.0 and 5.0 is recommended. - control_guidance_start (`float` or `List[float]`, *optional*, defaults to 0.0): - The percentage of total steps at which the controlnet starts applying. - control_guidance_end (`float` or `List[float]`, *optional*, defaults to 1.0): - The percentage of total steps at which the controlnet stops applying. - - Examples: - - Returns: - [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] or `tuple`: - [`~pipelines.stable_diffusion.StableDiffusionPipelineOutput`] if `return_dict` is True, otherwise a `tuple. - When returning a tuple, the first element is a list with the generated images, and the second element is a - list of `bool`s denoting whether the corresponding generated image likely represents "not-safe-for-work" - (nsfw) content, according to the `safety_checker`. - """ - controlnet = self.controlnet._orig_mod if is_compiled_module(self.controlnet) else self.controlnet - - # align format for control guidance - if not isinstance(control_guidance_start, list) and isinstance(control_guidance_end, list): - control_guidance_start = len(control_guidance_end) * [control_guidance_start] - elif not isinstance(control_guidance_end, list) and isinstance(control_guidance_start, list): - control_guidance_end = len(control_guidance_start) * [control_guidance_end] - elif not isinstance(control_guidance_start, list) and not isinstance(control_guidance_end, list): - mult = len(controlnet.nets) if isinstance(controlnet, MultiControlNetModel) else 1 - control_guidance_start, control_guidance_end = mult * [control_guidance_start], mult * [control_guidance_end] - - # 1. Check inputs. Raise error if not correct - self.check_inputs( - prompt, - image, - callback_steps, - negative_prompt, - prompt_embeds, - negative_prompt_embeds, - controlnet_conditioning_scale, - control_guidance_start, - control_guidance_end, - ) - - # 2. Define call parameters - if prompt is not None and isinstance(prompt, str): - batch_size = 1 - elif prompt is not None and isinstance(prompt, list): - batch_size = len(prompt) - else: - batch_size = prompt_embeds.shape[0] - - device = self._execution_device - # here `guidance_scale` is defined analog to the guidance weight `w` of equation (2) - # of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1` - # corresponds to doing no classifier free guidance. - do_classifier_free_guidance = guidance_scale > 1.0 - - if isinstance(controlnet, MultiControlNetModel) and isinstance(controlnet_conditioning_scale, float): - controlnet_conditioning_scale = [controlnet_conditioning_scale] * len(controlnet.nets) - - global_pool_conditions = ( - controlnet.config.global_pool_conditions - if isinstance(controlnet, ControlNetModel) - else controlnet.nets[0].config.global_pool_conditions - ) - guess_mode = guess_mode or global_pool_conditions - - # 3. Encode input prompt - text_encoder_lora_scale = cross_attention_kwargs.get("scale", None) if cross_attention_kwargs is not None else None - prompt_embeds = self._encode_prompt( - prompt, - device, - num_images_per_prompt, - do_classifier_free_guidance, - negative_prompt, - prompt_embeds=prompt_embeds, - negative_prompt_embeds=negative_prompt_embeds, - lora_scale=text_encoder_lora_scale, - ) - - # 4. Prepare image - if isinstance(controlnet, ControlNetModel): - image = self.prepare_image( - image=image, - width=width, - height=height, - batch_size=batch_size * num_images_per_prompt, - num_images_per_prompt=num_images_per_prompt, - device=device, - dtype=controlnet.dtype, - do_classifier_free_guidance=do_classifier_free_guidance, - guess_mode=guess_mode, - ) - height, width = image.shape[-2:] - elif isinstance(controlnet, MultiControlNetModel): - images = [] - - for image_ in image: - image_ = self.prepare_image( - image=image_, - width=width, - height=height, - batch_size=batch_size * num_images_per_prompt, - num_images_per_prompt=num_images_per_prompt, - device=device, - dtype=controlnet.dtype, - do_classifier_free_guidance=do_classifier_free_guidance, - guess_mode=guess_mode, - ) - - images.append(image_) - - image = images - height, width = image[0].shape[-2:] - else: - assert False - - # 5. Prepare timesteps - self.scheduler.set_timesteps(num_inference_steps, device=device) - timesteps = self.scheduler.timesteps - - # 6. Prepare latent variables - num_channels_latents = self.unet.config.in_channels - latents = self.prepare_latents( - batch_size * num_images_per_prompt, - num_channels_latents, - height, - width, - prompt_embeds.dtype, - device, - generator, - latents, - ) - - # 7. Prepare extra step kwargs. TODO: Logic should ideally just be moved out of the pipeline - extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta) - - # 7.1 Create tensor stating which controlnets to keep - controlnet_keep = [] - for i in range(len(timesteps)): - keeps = [ - 1.0 - float(i / len(timesteps) < s or (i + 1) / len(timesteps) > e) - for s, e in zip(control_guidance_start, control_guidance_end) - ] - controlnet_keep.append(keeps[0] if isinstance(controlnet, ControlNetModel) else keeps) - - # 8. Denoising loop - num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order - with self.progress_bar(total=num_inference_steps) as progress_bar: - for i, t in enumerate(timesteps): - # expand the latents if we are doing classifier free guidance - latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents - latent_model_input = self.scheduler.scale_model_input(latent_model_input, t) - - # controlnet(s) inference - if guess_mode and do_classifier_free_guidance: - # Infer ControlNet only for the conditional batch. - control_model_input = latents - control_model_input = self.scheduler.scale_model_input(control_model_input, t) - controlnet_prompt_embeds = prompt_embeds[:, :77, :].chunk(2)[1] - else: - control_model_input = latent_model_input - controlnet_prompt_embeds = prompt_embeds[:, :77, :] - - if isinstance(controlnet_keep[i], list): - cond_scale = [c * s for c, s in zip(controlnet_conditioning_scale, controlnet_keep[i])] - else: - controlnet_cond_scale = controlnet_conditioning_scale - if isinstance(controlnet_cond_scale, list): - controlnet_cond_scale = controlnet_cond_scale[0] - cond_scale = controlnet_cond_scale * controlnet_keep[i] - - down_block_res_samples, mid_block_res_sample = self.controlnet( - control_model_input, - t, - encoder_hidden_states=controlnet_prompt_embeds, - controlnet_cond=image, - conditioning_scale=cond_scale, - guess_mode=guess_mode, - return_dict=False, - ) - - if guess_mode and do_classifier_free_guidance: - # Infered ControlNet only for the conditional batch. - # To apply the output of ControlNet to both the unconditional and conditional batches, - # add 0 to the unconditional batch to keep it unchanged. - down_block_res_samples = [torch.cat([torch.zeros_like(d), d]) for d in down_block_res_samples] - mid_block_res_sample = torch.cat([torch.zeros_like(mid_block_res_sample), mid_block_res_sample]) - - # predict the noise residual - noise_pred = self.unet( - latent_model_input, - t, - encoder_hidden_states=prompt_embeds, - cross_attention_kwargs=cross_attention_kwargs, - down_block_additional_residuals=down_block_res_samples, - mid_block_additional_residual=mid_block_res_sample, - return_dict=False, - )[0] - - # perform guidance - if do_classifier_free_guidance: - noise_pred_uncond, noise_pred_text = noise_pred.chunk(2) - noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond) - - # compute the previous noisy sample x_t -> x_t-1 - latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs, return_dict=False)[0] - - # call the callback, if provided - if i == len(timesteps) - 1 or ((i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0): - progress_bar.update() - if callback is not None and i % callback_steps == 0: - callback(i, t, latents) - - # If we do sequential model offloading, let's offload unet and controlnet - # manually for max memory savings - if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None: - self.unet.to("cpu") - self.controlnet.to("cpu") - torch.cuda.empty_cache() - - if not output_type == "latent": - image = self.vae.decode(latents / self.vae.config.scaling_factor, return_dict=False)[0] - image, has_nsfw_concept = self.run_safety_checker(image, device, prompt_embeds.dtype) - else: - image = latents - has_nsfw_concept = None - - if has_nsfw_concept is None: - do_denormalize = [True] * image.shape[0] - else: - do_denormalize = [not has_nsfw for has_nsfw in has_nsfw_concept] - - image = self.image_processor.postprocess(image, output_type=output_type, do_denormalize=do_denormalize) - - # Offload last model to CPU - if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None: - self.final_offload_hook.offload() - - if not return_dict: - return (image, has_nsfw_concept) - - return StableDiffusionPipelineOutput(images=image, nsfw_content_detected=has_nsfw_concept)