CogView3Plus (original) (raw)

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion from Tsinghua University & ZhipuAI, by Wendi Zheng, Jiayan Teng, Zhuoyi Yang, Weihan Wang, Jidong Chen, Xiaotao Gu, Yuxiao Dong, Ming Ding, Jie Tang.

The abstract from the paper is:

Recent advancements in text-to-image generative systems have been largely driven by diffusion models. However, single-stage text-to-image diffusion models still face challenges, in terms of computational efficiency and the refinement of image details. To tackle the issue, we propose CogView3, an innovative cascaded framework that enhances the performance of text-to-image diffusion. CogView3 is the first model implementing relay diffusion in the realm of text-to-image generation, executing the task by first creating low-resolution images and subsequently applying relay-based super-resolution. This methodology not only results in competitive text-to-image outputs but also greatly reduces both training and inference costs. Our experimental results demonstrate that CogView3 outperforms SDXL, the current state-of-the-art open-source text-to-image diffusion model, by 77.0% in human evaluations, all while requiring only about 1/2 of the inference time. The distilled variant of CogView3 achieves comparable performance while only utilizing 1/10 of the inference time by SDXL.

Make sure to check out the Schedulers guide to learn how to explore the tradeoff between scheduler speed and quality, and see the reuse components across pipelines section to learn how to efficiently load the same components into multiple pipelines.

This pipeline was contributed by zRzRzRzRzRzRzR. The original codebase can be found here. The original weights can be found under hf.co/THUDM.

CogView3PlusPipeline

class diffusers.CogView3PlusPipeline

< source >

( tokenizer: T5Tokenizer text_encoder: T5EncoderModel vae: AutoencoderKL transformer: CogView3PlusTransformer2DModel scheduler: typing.Union[diffusers.schedulers.scheduling_ddim_cogvideox.CogVideoXDDIMScheduler, diffusers.schedulers.scheduling_dpm_cogvideox.CogVideoXDPMScheduler] )

Parameters

• vae (AutoencoderKL) — Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.
• text_encoder (T5EncoderModel) — Frozen text-encoder. CogView3Plus usesT5; specifically thet5-v1_1-xxl variant.
• tokenizer (T5Tokenizer) — Tokenizer of classT5Tokenizer.
• transformer (CogView3PlusTransformer2DModel) — A text conditioned CogView3PlusTransformer2DModel to denoise the encoded image latents.
• scheduler (SchedulerMixin) — A scheduler to be used in combination with transformer to denoise the encoded image latents.

Pipeline for text-to-image generation using CogView3Plus.

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.)

__call__

< source >

( prompt: typing.Union[str, typing.List[str], NoneType] = None negative_prompt: typing.Union[str, typing.List[str], NoneType] = None height: typing.Optional[int] = None width: typing.Optional[int] = None num_inference_steps: int = 50 timesteps: typing.Optional[typing.List[int]] = None guidance_scale: float = 5.0 num_images_per_prompt: int = 1 eta: float = 0.0 generator: typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None latents: typing.Optional[torch.FloatTensor] = None prompt_embeds: typing.Optional[torch.FloatTensor] = None negative_prompt_embeds: typing.Optional[torch.FloatTensor] = None original_size: typing.Optional[typing.Tuple[int, int]] = None crops_coords_top_left: typing.Tuple[int, int] = (0, 0) output_type: str = 'pil' return_dict: bool = True callback_on_step_end: typing.Union[typing.Callable[[int, int, typing.Dict], NoneType], diffusers.callbacks.PipelineCallback, diffusers.callbacks.MultiPipelineCallbacks, NoneType] = None callback_on_step_end_tensor_inputs: typing.List[str] = ['latents'] max_sequence_length: int = 224 ) → CogView3PipelineOutput or tuple

Parameters

• prompt (str or List[str], optional) — The prompt or prompts to guide the image generation. If not defined, one has to pass prompt_embeds.
• negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. If not defined, one has to passnegative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
• height (int, optional, defaults to self.transformer.config.sample_size * self.vae_scale_factor) — The height in pixels of the generated image. If not provided, it is set to 1024.
• width (int, optional, defaults to self.transformer.config.sample_size * self.vae_scale_factor) — The width in pixels of the generated image. If not provided it is set to 1024.
• 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.
• timesteps (List[int], optional) — Custom timesteps to use for the denoising process with schedulers which support a timesteps argument in their set_timesteps method. If not defined, the default behavior when num_inference_steps is passed will be used. Must be in descending order.
• guidance_scale (float, optional, defaults to 5.0) — Guidance scale as defined in Classifier-Free Diffusion Guidance.guidance_scale is defined as w of equation 2. of Imagen Paper. 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.
• num_images_per_prompt (int, optional, defaults to 1) — The number of images to generate per prompt.
• generator (torch.Generator or List[torch.Generator], optional) — One or a list of torch generator(s)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.
• original_size (Tuple[int], optional, defaults to (1024, 1024)) — If original_size is not the same as target_size the image will appear to be down- or upsampled.original_size defaults to (height, width) if not specified. Part of SDXL’s micro-conditioning as explained in section 2.2 ofhttps://huggingface.co/papers/2307.01952.
• crops_coords_top_left (Tuple[int], optional, defaults to (0, 0)) —crops_coords_top_left can be used to generate an image that appears to be “cropped” from the positioncrops_coords_top_left downwards. Favorable, well-centered images are usually achieved by settingcrops_coords_top_left to (0, 0). Part of SDXL’s micro-conditioning as explained in section 2.2 ofhttps://huggingface.co/papers/2307.01952.
• output_type (str, optional, defaults to "pil") — The output format of the generate image. Choose betweenPIL: PIL.Image.Image or np.array.
• return_dict (bool, optional, defaults to True) — Whether or not to return a ~pipelines.stable_diffusion_xl.StableDiffusionXLPipelineOutput instead of a plain tuple.
• attention_kwargs (dict, optional) — A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined underself.processor indiffusers.models.attention_processor.
• callback_on_step_end (Callable, optional) — A function that calls at the end of each denoising steps during the inference. The function is called with the following arguments: callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict). callback_kwargs will include a list of all tensors as specified bycallback_on_step_end_tensor_inputs.
• callback_on_step_end_tensor_inputs (List, optional) — The list of tensor inputs for the callback_on_step_end function. The tensors specified in the list will be passed as callback_kwargs argument. You will only be able to include variables listed in the._callback_tensor_inputs attribute of your pipeline class.
• max_sequence_length (int, defaults to 224) — Maximum sequence length in encoded prompt. Can be set to other values but may lead to poorer results.

CogView3PipelineOutput if return_dict is True, otherwise atuple. When returning a tuple, the first element is a list with the generated images.

Function invoked when calling the pipeline for generation.

Examples:

import torch from diffusers import CogView3PlusPipeline

pipe = CogView3PlusPipeline.from_pretrained("THUDM/CogView3-Plus-3B", torch_dtype=torch.bfloat16) pipe.to("cuda")

prompt = "A photo of an astronaut riding a horse on mars" image = pipe(prompt).images[0] image.save("output.png")

encode_prompt

< source >

( prompt: typing.Union[str, typing.List[str]] negative_prompt: typing.Union[str, typing.List[str], NoneType] = None do_classifier_free_guidance: bool = True num_images_per_prompt: int = 1 prompt_embeds: typing.Optional[torch.Tensor] = None negative_prompt_embeds: typing.Optional[torch.Tensor] = None max_sequence_length: int = 224 device: typing.Optional[torch.device] = None dtype: typing.Optional[torch.dtype] = None )

Parameters

• prompt (str or List[str], optional) — prompt to be encoded
• negative_prompt (str or List[str], optional) — The prompt or prompts not to guide the image generation. If not defined, one has to passnegative_prompt_embeds instead. Ignored when not using guidance (i.e., ignored if guidance_scale is less than 1).
• do_classifier_free_guidance (bool, optional, defaults to True) — Whether to use classifier free guidance or not.
• num_images_per_prompt (int, optional, defaults to 1) — Number of images that should be generated per prompt. torch device to place the resulting embeddings on
• prompt_embeds (torch.Tensor, 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.Tensor, 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.
• max_sequence_length (int, defaults to 224) — Maximum sequence length in encoded prompt. Can be set to other values but may lead to poorer results.
• device — (torch.device, optional): torch device
• dtype — (torch.dtype, optional): torch dtype

Encodes the prompt into text encoder hidden states.

CogView3PipelineOutput

class diffusers.pipelines.cogview3.pipeline_output.CogView3PipelineOutput

< source >

( images: typing.Union[typing.List[PIL.Image.Image], numpy.ndarray] )

Parameters

• images (List[PIL.Image.Image] or np.ndarray) — List of denoised PIL images of length batch_size or numpy array of shape (batch_size, height, width, num_channels). PIL images or numpy array present the denoised images of the diffusion pipeline.

Output class for CogView3 pipelines.

< > Update on GitHub