diff --git a/docs/source/en/api/pipelines/stable_diffusion/overview.md b/docs/source/en/api/pipelines/stable_diffusion/overview.md index 2d2de39c91a8..b5ed95e9c17c 100644 --- a/docs/source/en/api/pipelines/stable_diffusion/overview.md +++ b/docs/source/en/api/pipelines/stable_diffusion/overview.md @@ -85,7 +85,7 @@ The table below summarizes the available Stable Diffusion pipelines, their suppo - StableDiffusionPipelineSafe + StableDiffusionPipelineSafe (deprecated; no doc page) filtered text-to-image diff --git a/docs/source/zh/optimization/speed-memory-optims.md b/docs/source/zh/optimization/speed-memory-optims.md index 666ae863c0e1..075e3f1159dc 100644 --- a/docs/source/zh/optimization/speed-memory-optims.md +++ b/docs/source/zh/optimization/speed-memory-optims.md @@ -15,9 +15,9 @@ http://www.apache.org/licenses/LICENSE-2.0 > [!TIP] > 查看 [torch.compile](./fp16#torchcompile) 指南以了解更多关于编译以及如何在此处应用的信息。例如，区域编译可以显著减少编译时间，而不会放弃任何加速。 -对于图像生成，结合量化和[模型卸载](./memory#model-offloading)通常可以在质量、速度和内存之间提供最佳权衡。组卸载对于图像生成效果不佳，因为如果计算内核更快完成，通常不可能*完全*重叠数据传输。这会导致 CPU 和 GPU 之间的一些通信开销。 +对于图像生成，结合量化和[模型卸载](./memory#模型卸载)通常可以在质量、速度和内存之间提供最佳权衡。组卸载对于图像生成效果不佳，因为如果计算内核更快完成，通常不可能*完全*重叠数据传输。这会导致 CPU 和 GPU 之间的一些通信开销。 -对于视频生成，结合量化和[组卸载](./memory#group-offloading)往往更好，因为视频模型更受计算限制。 +对于视频生成，结合量化和[组卸载](./memory#组卸载)往往更好，因为视频模型更受计算限制。 下表提供了优化策略组合及其对 Flux 延迟和内存使用的影响的比较。 @@ -113,7 +113,7 @@ pipeline( -[组卸载](./memory#group-offloading) 将单个管道组件（如变换器模型）的内部层移动到 GPU 进行计算，并在不需要时将其卸载。同时，它使用 [CUDA 流](./memory#cuda-stream) 功能来预取下一层以执行。 +[组卸载](./memory#组卸载) 将单个管道组件（如变换器模型）的内部层移动到 GPU 进行计算，并在不需要时将其卸载。同时，它使用 [CUDA 流](./memory#cuda-stream) 功能来预取下一层以执行。 通过重叠计算和数据传输，它比模型 CPU 卸载更快，同时还能节省内存。 diff --git a/docs/source/zh/tutorials/using_peft_for_inference.md b/docs/source/zh/tutorials/using_peft_for_inference.md index 1531c4e95560..29d9df2c492a 100644 --- a/docs/source/zh/tutorials/using_peft_for_inference.md +++ b/docs/source/zh/tutorials/using_peft_for_inference.md @@ -137,7 +137,7 @@ pipeline.unet = torch.compile(pipeline.unet, mode="reduce-overhead", fullgraph=T pipeline("A bowl of ramen shaped like a cute kawaii bear").images[0] ``` -如果你想在编译模型后配合多个 LoRA 一起使用，又不想每次都重新编译，可以查看下文的 [hotswapping](#hotswapping) 部分。 +如果你想在编译模型后配合多个 LoRA 一起使用，又不想每次都重新编译，可以查看下文的 [hotswapping](#热切换) 部分。 ## 权重缩放 diff --git a/examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py b/examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py index 3c7015458c8d..318db82661cc 100644 --- a/examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py +++ b/examples/advanced_diffusion_training/train_dreambooth_lora_flux_advanced.py @@ -421,7 +421,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=512, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--validation_prompt", diff --git a/examples/community/README.md b/examples/community/README.md index 67d241c153ad..f5c3357157e0 100644 --- a/examples/community/README.md +++ b/examples/community/README.md @@ -56,8 +56,8 @@ Please also check out our [Community Scripts](https://github.com/huggingface/dif | Stable Diffusion Mixture Tiling Pipeline SDXL | A pipeline generates cohesive images by integrating multiple diffusion processes, each focused on a specific image region and considering boundary effects for smooth blending | [Stable Diffusion Mixture Tiling Pipeline SDXL](#stable-diffusion-mixture-tiling-pipeline-sdxl) | [![Hugging Face Space](https://img.shields.io/badge/🤗%20Hugging%20Face-Space-yellow)](https://huggingface.co/spaces/elismasilva/mixture-of-diffusers-sdxl-tiling) | [Eliseu Silva](https://github.com/DEVAIEXP/) | | Stable Diffusion MoD ControlNet Tile SR Pipeline SDXL | This is an advanced pipeline that leverages ControlNet Tile and Mixture-of-Diffusers techniques, integrating tile diffusion directly into the latent space denoising process. Designed to overcome the limitations of conventional pixel-space tile processing, this pipeline delivers Super Resolution (SR) upscaling for higher-quality images, reduced processing time, and greater adaptability. | [Stable Diffusion MoD ControlNet Tile SR Pipeline SDXL](#stable-diffusion-mod-controlnet-tile-sr-pipeline-sdxl) | [![Hugging Face Space](https://img.shields.io/badge/🤗%20Hugging%20Face-Space-yellow)](https://huggingface.co/spaces/elismasilva/mod-control-tile-upscaler-sdxl) | [Eliseu Silva](https://github.com/DEVAIEXP/) | | FABRIC - Stable Diffusion with feedback Pipeline | pipeline supports feedback from liked and disliked images | [Stable Diffusion Fabric Pipeline](#stable-diffusion-fabric-pipeline) | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/stable_diffusion_fabric.ipynb)| [Shauray Singh](https://shauray8.github.io/about_shauray/) | -| sketch inpaint - Inpainting with non-inpaint Stable Diffusion | sketch inpaint much like in automatic1111 | [Masked Im2Im Stable Diffusion Pipeline](#stable-diffusion-masked-im2im) | - | [Anatoly Belikov](https://github.com/noskill) | -| sketch inpaint xl - Inpainting with non-inpaint Stable Diffusion | sketch inpaint much like in automatic1111 | [Masked Im2Im Stable Diffusion XL Pipeline](#stable-diffusion-xl-masked-im2im) | - | [Anatoly Belikov](https://github.com/noskill) | +| sketch inpaint - Inpainting with non-inpaint Stable Diffusion | sketch inpaint much like in automatic1111 | [Masked Im2Im Stable Diffusion Pipeline](#masked-im2im-stable-diffusion-pipeline) | - | [Anatoly Belikov](https://github.com/noskill) | +| sketch inpaint xl - Inpainting with non-inpaint Stable Diffusion | sketch inpaint much like in automatic1111 | [Masked Im2Im Stable Diffusion XL Pipeline](#masked-im2im-stable-diffusion-pipeline-xl) | - | [Anatoly Belikov](https://github.com/noskill) | | prompt-to-prompt | change parts of a prompt and retain image structure (see [paper page](https://prompt-to-prompt.github.io/)) | [Prompt2Prompt Pipeline](#prompt2prompt-pipeline) | [Notebook](https://github.com/huggingface/notebooks/blob/main/diffusers/prompt_2_prompt_pipeline.ipynb) | [Umer H. Adil](https://twitter.com/UmerHAdil) | | Latent Consistency Pipeline | Implementation of [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://huggingface.co/papers/2310.04378) | [Latent Consistency Pipeline](#latent-consistency-pipeline) | - | [Simian Luo](https://github.com/luosiallen) | | Latent Consistency Img2img Pipeline | Img2img pipeline for Latent Consistency Models | [Latent Consistency Img2Img Pipeline](#latent-consistency-img2img-pipeline) | - | [Logan Zoellner](https://github.com/nagolinc) | diff --git a/examples/controlnet/train_controlnet_sd3.py b/examples/controlnet/train_controlnet_sd3.py index fc2111db386b..e0e296bacb7f 100644 --- a/examples/controlnet/train_controlnet_sd3.py +++ b/examples/controlnet/train_controlnet_sd3.py @@ -585,7 +585,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=77, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--dataset_preprocess_batch_size", type=int, default=1000, help="Batch size for preprocessing dataset." diff --git a/examples/dreambooth/train_dreambooth_flux.py b/examples/dreambooth/train_dreambooth_flux.py index df3e03e70d44..ffaa7de1ad86 100644 --- a/examples/dreambooth/train_dreambooth_flux.py +++ b/examples/dreambooth/train_dreambooth_flux.py @@ -329,7 +329,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=77, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--validation_prompt", diff --git a/examples/dreambooth/train_dreambooth_lora_flux.py b/examples/dreambooth/train_dreambooth_lora_flux.py index 9bae56da2377..3375a583e2f2 100644 --- a/examples/dreambooth/train_dreambooth_lora_flux.py +++ b/examples/dreambooth/train_dreambooth_lora_flux.py @@ -349,7 +349,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=512, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--validation_prompt", diff --git a/examples/dreambooth/train_dreambooth_lora_flux2.py b/examples/dreambooth/train_dreambooth_lora_flux2.py index 8cb5437c7093..85faea833bb9 100644 --- a/examples/dreambooth/train_dreambooth_lora_flux2.py +++ b/examples/dreambooth/train_dreambooth_lora_flux2.py @@ -353,7 +353,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=512, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--text_encoder_out_layers", diff --git a/examples/dreambooth/train_dreambooth_lora_flux2_img2img.py b/examples/dreambooth/train_dreambooth_lora_flux2_img2img.py index 7397c2abef98..2ba694405c48 100644 --- a/examples/dreambooth/train_dreambooth_lora_flux2_img2img.py +++ b/examples/dreambooth/train_dreambooth_lora_flux2_img2img.py @@ -354,7 +354,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=512, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--validation_prompt", diff --git a/examples/dreambooth/train_dreambooth_lora_flux2_klein.py b/examples/dreambooth/train_dreambooth_lora_flux2_klein.py index 684e123c6e55..3cad3f2ac561 100644 --- a/examples/dreambooth/train_dreambooth_lora_flux2_klein.py +++ b/examples/dreambooth/train_dreambooth_lora_flux2_klein.py @@ -353,7 +353,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=512, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--text_encoder_out_layers", diff --git a/examples/dreambooth/train_dreambooth_lora_flux2_klein_img2img.py b/examples/dreambooth/train_dreambooth_lora_flux2_klein_img2img.py index f3ab6916193e..df56f2557213 100644 --- a/examples/dreambooth/train_dreambooth_lora_flux2_klein_img2img.py +++ b/examples/dreambooth/train_dreambooth_lora_flux2_klein_img2img.py @@ -355,7 +355,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=512, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--validation_prompt", diff --git a/examples/dreambooth/train_dreambooth_lora_flux_kontext.py b/examples/dreambooth/train_dreambooth_lora_flux_kontext.py index 6884cc58ea5e..f2e8e931b5dd 100644 --- a/examples/dreambooth/train_dreambooth_lora_flux_kontext.py +++ b/examples/dreambooth/train_dreambooth_lora_flux_kontext.py @@ -368,7 +368,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=512, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--validation_prompt", diff --git a/examples/dreambooth/train_dreambooth_lora_lumina2.py b/examples/dreambooth/train_dreambooth_lora_lumina2.py index 9932f3dfd878..f786b62fbecc 100644 --- a/examples/dreambooth/train_dreambooth_lora_lumina2.py +++ b/examples/dreambooth/train_dreambooth_lora_lumina2.py @@ -288,7 +288,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=256, - help="Maximum sequence length to use with with the Gemma2 model", + help="Maximum sequence length to use with the Gemma2 model", ) parser.add_argument( "--system_prompt", diff --git a/examples/dreambooth/train_dreambooth_lora_sana.py b/examples/dreambooth/train_dreambooth_lora_sana.py index 4e70d6ab1b92..7b79d33496a2 100644 --- a/examples/dreambooth/train_dreambooth_lora_sana.py +++ b/examples/dreambooth/train_dreambooth_lora_sana.py @@ -308,7 +308,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=300, - help="Maximum sequence length to use with with the Gemma model", + help="Maximum sequence length to use with the Gemma model", ) parser.add_argument( "--complex_human_instruction", diff --git a/examples/dreambooth/train_dreambooth_lora_sd3.py b/examples/dreambooth/train_dreambooth_lora_sd3.py index a1b3e34106d4..6f5c61781f89 100644 --- a/examples/dreambooth/train_dreambooth_lora_sd3.py +++ b/examples/dreambooth/train_dreambooth_lora_sd3.py @@ -339,7 +339,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=77, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--validation_prompt", diff --git a/examples/dreambooth/train_dreambooth_lora_z_image.py b/examples/dreambooth/train_dreambooth_lora_z_image.py index ef2f6870df30..e116803ee859 100644 --- a/examples/dreambooth/train_dreambooth_lora_z_image.py +++ b/examples/dreambooth/train_dreambooth_lora_z_image.py @@ -353,7 +353,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=512, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( diff --git a/examples/dreambooth/train_dreambooth_sd3.py b/examples/dreambooth/train_dreambooth_sd3.py index 2151cd009a42..7419d8763756 100644 --- a/examples/dreambooth/train_dreambooth_sd3.py +++ b/examples/dreambooth/train_dreambooth_sd3.py @@ -315,7 +315,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=77, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--validation_prompt", diff --git a/examples/research_projects/sana/train_sana_sprint_diffusers.py b/examples/research_projects/sana/train_sana_sprint_diffusers.py index d127fee5fd0d..bd164ea2119e 100644 --- a/examples/research_projects/sana/train_sana_sprint_diffusers.py +++ b/examples/research_projects/sana/train_sana_sprint_diffusers.py @@ -359,7 +359,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=300, - help="Maximum sequence length to use with with the Gemma model", + help="Maximum sequence length to use with the Gemma model", ) parser.add_argument( "--validation_prompt", diff --git a/examples/research_projects/sd3_lora_colab/train_dreambooth_lora_sd3_miniature.py b/examples/research_projects/sd3_lora_colab/train_dreambooth_lora_sd3_miniature.py index d73aab73630a..63b8e194f620 100644 --- a/examples/research_projects/sd3_lora_colab/train_dreambooth_lora_sd3_miniature.py +++ b/examples/research_projects/sd3_lora_colab/train_dreambooth_lora_sd3_miniature.py @@ -235,7 +235,7 @@ def parse_args(input_args=None): "--max_sequence_length", type=int, default=77, - help="Maximum sequence length to use with with the T5 text encoder", + help="Maximum sequence length to use with the T5 text encoder", ) parser.add_argument( "--validation_prompt", diff --git a/src/diffusers/pipelines/flux/pipeline_flux_controlnet.py b/src/diffusers/pipelines/flux/pipeline_flux_controlnet.py index e7792d667f16..1483d6cf98b7 100644 --- a/src/diffusers/pipelines/flux/pipeline_flux_controlnet.py +++ b/src/diffusers/pipelines/flux/pipeline_flux_controlnet.py @@ -368,9 +368,6 @@ def encode_prompt( pooled_prompt_embeds (`torch.FloatTensor`, *optional*): Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not provided, pooled text embeddings will be generated from `prompt` input argument. - clip_skip (`int`, *optional*): - Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that - the output of the pre-final layer will be used for computing the prompt embeddings. lora_scale (`float`, *optional*): A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded. """ diff --git a/src/diffusers/pipelines/hunyuan_video1_5/pipeline_hunyuan_video1_5.py b/src/diffusers/pipelines/hunyuan_video1_5/pipeline_hunyuan_video1_5.py index a0adff493ac0..7232ebbee5b8 100644 --- a/src/diffusers/pipelines/hunyuan_video1_5/pipeline_hunyuan_video1_5.py +++ b/src/diffusers/pipelines/hunyuan_video1_5/pipeline_hunyuan_video1_5.py @@ -352,7 +352,7 @@ def encode_prompt( torch device batch_size (`int`): batch size of prompts, defaults to 1 - num_images_per_prompt (`int`): + num_videos_per_prompt (`int`): number of images that should be generated per prompt prompt_embeds (`torch.Tensor`, *optional*): Pre-generated text embeddings. If not provided, text embeddings will be generated from `prompt` input diff --git a/src/diffusers/pipelines/hunyuan_video1_5/pipeline_hunyuan_video1_5_image2video.py b/src/diffusers/pipelines/hunyuan_video1_5/pipeline_hunyuan_video1_5_image2video.py index 1d33c2ae188f..71a36a1c51cd 100644 --- a/src/diffusers/pipelines/hunyuan_video1_5/pipeline_hunyuan_video1_5_image2video.py +++ b/src/diffusers/pipelines/hunyuan_video1_5/pipeline_hunyuan_video1_5_image2video.py @@ -440,7 +440,7 @@ def encode_prompt( torch device batch_size (`int`): batch size of prompts, defaults to 1 - num_images_per_prompt (`int`): + num_videos_per_prompt (`int`): number of images that should be generated per prompt prompt_embeds (`torch.Tensor`, *optional*): Pre-generated text embeddings. If not provided, text embeddings will be generated from `prompt` input diff --git a/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky.py b/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky.py index 1ce885b21f5b..56098a0a7550 100644 --- a/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky.py +++ b/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky.py @@ -188,7 +188,7 @@ def __init__( self.prompt_template = "\n".join( [ - "<|im_start|>system\nYou are a promt engineer. Describe the video in detail.", + "<|im_start|>system\nYou are a prompt engineer. Describe the video in detail.", "Describe how the camera moves or shakes, describe the zoom and view angle, whether it follows the objects.", "Describe the location of the video, main characters or objects and their action.", "Describe the dynamism of the video and presented actions.", @@ -326,7 +326,6 @@ def _encode_prompt_qwen( Args: prompt (str | list[str]): Input prompt or list of prompts device (torch.device): Device to run encoding on - num_videos_per_prompt (int): Number of videos to generate per prompt max_sequence_length (int): Maximum sequence length for tokenization dtype (torch.dtype): Data type for embeddings @@ -395,7 +394,6 @@ def _encode_prompt_clip( Args: prompt (str | list[str]): Input prompt or list of prompts device (torch.device): Device to run encoding on - num_videos_per_prompt (int): Number of videos to generate per prompt dtype (torch.dtype): Data type for embeddings Returns: diff --git a/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_i2i.py b/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_i2i.py index 0a8382d6031f..507991374dd2 100644 --- a/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_i2i.py +++ b/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_i2i.py @@ -174,7 +174,7 @@ def __init__( tokenizer_2=tokenizer_2, scheduler=scheduler, ) - self.prompt_template = "<|im_start|>system\nYou are a promt engineer. Based on the provided source image (first image) and target image (second image), create an interesting text prompt that can be used together with the source image to create the target image:<|im_end|><|im_start|>user{}<|vision_start|><|image_pad|><|vision_end|><|im_end|>" + self.prompt_template = "<|im_start|>system\nYou are a prompt engineer. Based on the provided source image (first image) and target image (second image), create an interesting text prompt that can be used together with the source image to create the target image:<|im_end|><|im_start|>user{}<|vision_start|><|image_pad|><|vision_end|><|im_end|>" self.prompt_template_encode_start_idx = 55 self.vae_scale_factor_spatial = 8 diff --git a/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_i2v.py b/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_i2v.py index 634305daff6b..d5bfe362a83c 100644 --- a/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_i2v.py +++ b/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_i2v.py @@ -185,7 +185,7 @@ def __init__( self.prompt_template = "\n".join( [ - "<|im_start|>system\nYou are a promt engineer. Describe the video in detail.", + "<|im_start|>system\nYou are a prompt engineer. Describe the video in detail.", "Describe how the camera moves or shakes, describe the zoom and view angle, whether it follows the objects.", "Describe the location of the video, main characters or objects and their action.", "Describe the dynamism of the video and presented actions.", diff --git a/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_t2i.py b/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_t2i.py index 2a58d4bed33a..c39f9c1b3333 100644 --- a/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_t2i.py +++ b/src/diffusers/pipelines/kandinsky5/pipeline_kandinsky_t2i.py @@ -175,7 +175,7 @@ def __init__( scheduler=scheduler, ) - self.prompt_template = "<|im_start|>system\nYou are a promt engineer. Describe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|>\n<|im_start|>user\n{}<|im_end|>" + self.prompt_template = "<|im_start|>system\nYou are a prompt engineer. Describe the image by detailing the color, shape, size, texture, quantity, text, spatial relationships of the objects and background:<|im_end|>\n<|im_start|>user\n{}<|im_end|>" self.prompt_template_encode_start_idx = 41 self.vae_scale_factor_spatial = 8 diff --git a/src/diffusers/pipelines/ltx/pipeline_ltx_latent_upsample.py b/src/diffusers/pipelines/ltx/pipeline_ltx_latent_upsample.py index fbf98ce976d9..6f325237a248 100644 --- a/src/diffusers/pipelines/ltx/pipeline_ltx_latent_upsample.py +++ b/src/diffusers/pipelines/ltx/pipeline_ltx_latent_upsample.py @@ -97,7 +97,7 @@ def adain_filter_latent(self, latents: torch.Tensor, reference_latents: torch.Te tensor. Args: - latent (`torch.Tensor`): + latents (`torch.Tensor`): Input latents to normalize reference_latents (`torch.Tensor`): The reference latents providing style statistics. diff --git a/src/diffusers/pipelines/ltx2/pipeline_ltx2_latent_upsample.py b/src/diffusers/pipelines/ltx2/pipeline_ltx2_latent_upsample.py index 4d085ca8f4ca..8aa72a425e1c 100644 --- a/src/diffusers/pipelines/ltx2/pipeline_ltx2_latent_upsample.py +++ b/src/diffusers/pipelines/ltx2/pipeline_ltx2_latent_upsample.py @@ -171,7 +171,7 @@ def adain_filter_latent(self, latents: torch.Tensor, reference_latents: torch.Te tensor. Args: - latent (`torch.Tensor`): + latents (`torch.Tensor`): Input latents to normalize reference_latents (`torch.Tensor`): The reference latents providing style statistics.