AnimateDiff

AnimateDiff copied to clipboard

When running `script-animate`, Python generates caches but these shouldn't be included in the repository. This pull request adds a basic .gitignore file to ignore these folders.

jamesWalker55

peronalized -> personalized

eltociear

#14 git clone https://huggingface.co/runwayml/stable-diffusion-v1-5 models/StableDiffusion/

sdbds

huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'models/StableDiffusion/stable-diffusion-v1-5'. Use `repo_type` argument if needed.

13

huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'models/StableDiffusion/stable-diffusion-v1-5'. Use `repo_type` argument if needed. (animatediff) G:\AI\AnimateDiff> win10 conda3 pytorch2.01 cuda118. 模型都下好，放在G:\AI\AnimateDiff\models\StableDiffusion,文件名为stable-diffusion-v1-5 .safetensors. 还是报这个错误。

isamu2025

Very little movement with mm_sd_v15.ckpt?

1

Is it intended for images to have barely any movement with the mm_sd_v15 ckpt? See: 

Ericxgao

How to generate videos based on StableDiffusion v1.5

2

Thanks for your great work! Could you provide scripts or configs to produce videos based on SD v1.5?

YBYBZhang

Are Textual Inversion embeddings supported?

1

In the examples in `configs/prompts/`, the prompts contain references to textual inversion embeddings like `badhandv4`, `easynegative`, `ng_deepnegative_v1_75t`: ```yaml n_prompt: - "easynegative,bad_construction,bad_structure,bad_wail,bad_windows,blurry,cloned_window,cropped,deformed,disfigured,error,extra_windows,extra_chimney,extra_door,extra_structure,extra_frame,fewer_digits,fused_structure,gross_proportions,jpeg_artifacts,long_roof,low_quality,structure_limbs,missing_windows,missing_doors,missing_roofs,mutated_structure,mutation,normal_quality,out_of_frame,owres,poorly_drawn_structure,poorly_drawn_house,signature,text,too_many_windows,ugly,username,uta,watermark,worst_quality" ``` From looking at the source code I'm not...

jamesWalker55

大佬们好！ 这个稳定性已经很好了，工程库里面我没发现是如何提升帧与帧之间的稳定性的， prompt参数都是生成单帧的，请问如何做到如此大的相似性？ 之前我有关注过下面这个，他们的思路给前景的关键词，用于锁定固定的内容。 https://github.com/ashen-sensored/sd_webui_masactrl https://arxiv.org/abs/2304.08465 加油！

Erwin11

Image2Anim?

1

Are you planning to implement image-to-animation pipeline?

Pakuronn

Generating different number of frames

12

Hi! Thanks for a very interesting paper, I wonder if you've tried generating shorter/longer clips? I see that there is `temporal_position_encoding_max_len=24` which limits the length to be 24 frames, but...

bonlime