Stability-AI/generative-models

Issues

• Question about the training time?

  #409 opened 2 months ago by leilai125
  1

• Error when trying to install "pip install -r requirements/pt2.txt" in python 3.10.11

  #414 opened 2 months ago by oftavira
  4

• SV4D: Custom Video with more than 21 Frames

  #420 opened 24 days ago by Vinayak-VG
  0

• Error occur when training toy example

  #417 opened a month ago by koojahyeok
  2

• The CKPT_PATH of the txt2img-clipl.yaml

  #367 opened 5 months ago by RanJason-Code
  1

• UnboundLocalError: local variable 'input_image' referenced before assignment

  #361 opened 6 months ago by qiuyuzhao
  2

• What is the cost for training LADD?

  #418 opened a month ago by HoiM
  0

• A question

  #390 opened a month ago by Dumeowmeow
  0

• SpatialTransformer: Found context dims [2048] of depth 1, which does not match the specified 'depth' of 2. Setting context_dim to [2048, 2048] now.

  #416 opened 2 months ago by LukeLIN-web
  1

• OSError: No such device (os error 19)

  #406 opened 3 months ago by ezone1987
  1

• streamlit run scripts/demo/sampling.py fail to access the url

  #412 opened 2 months ago by fenglincong
  0

• Only noisy output video of sv3d_u

  #411 opened 2 months ago by URRealHero
  0

• how to train sv3d

  #380 opened 2 months ago by shewangmu
  3

• Error loading safetensor files for svd and sv3d

  #405 opened 3 months ago by mich889
  0

• How to run SV3D_u on MacBook with M1 chip

  #360 opened 6 months ago by alisonqiu
  1

• Failure building wheel for tokenizers on M1

  #401 opened 3 months ago by mich889
  1

• Failed Building wheel for tokenizers

  #402 opened 3 months ago by mich889
  1

• Plan to release pretrained weight for the discriminator for Latent Adversarial Diffusion Distillation?

  #404 opened 3 months ago by SherryXTChen
  0

• Copying checkpoint (sv3d_u.safetensors) takes too long

  #403 opened 3 months ago by lkim0402
  0

• How to train SV4D

  #400 opened 3 months ago by Ysz2022
  0

• sv4d sigma_cond

  #399 opened 3 months ago by yjhong89
  0

• fixing issue in generative-models/sgm/models /diffusion.py

  #397 opened 3 months ago by sijang
  0

• Enabling Multi-GPU in SVD

  #396 opened 3 months ago by Benjamin-So
  0

• sv4d,torch.cuda.OutOfMemoryError

  #393 opened 4 months ago by shengxiao-zhou
  12

• where is the checkpoint of encoder of sv3d

  #395 opened 3 months ago by shewangmu
  3

• How to run Stable Video 4D on Google Colab?

  #388 opened 4 months ago by kaitas
  2

• run SV4D on DAVIS dataset

  #389 opened 4 months ago by yuzhongruicn
  1

• NameError: name 'xformers' is not defined

  #387 opened 4 months ago by hpandeycodeit
  1

• What is the definition of elevation in SV3D_p?

  #379 opened 4 months ago by rocksat
  1

• ControlNet for SV3D

  #383 opened 4 months ago by YuzhiChen001
  0

• 💡Stable Diffusion run on blockchain

  #382 opened 4 months ago by jujubeja
  1

• Question about VAE. Getting Help！！！

  #381 opened 4 months ago by liujf69
  0

• About performance of SV3D

  #374 opened 4 months ago by Colezwhy
  0

• To solve connection Error due to Lib Path Collision

  #377 opened 4 months ago by dablro12
  0

• "No operator found for `memory_efficient_attention_forward` with inputs" issue on Mac Pro M1

  #376 opened 5 months ago by LinearFalcon
  0

• LVD-152M

  #375 opened 5 months ago by haoxurt
  0

• Are there models trained in "x0" mode?

  #373 opened 5 months ago by gaopinghai
  0

• Connection Error

  #372 opened 5 months ago by trunliu
  0

• Code of Stable3 medium released ??

  #370 opened 5 months ago by yjhong89
  1

• How to merge the vae encoder weights in svd-xt to first_stage_model.encoder in sv3d_p.safetensors ?

  #371 opened 5 months ago by zhaosheng-thu
  0

• generated video from sd3d_p is more than 20M and cannot be played

  #366 opened 5 months ago by gracesolver
  1

• Large memory requirement when implementing sds loss using SV3D

  #356 opened 7 months ago by yifliu3
  2

• svd effect

  #369 opened 5 months ago by minmin0516
  0

• How to run this repo on cpu with autocast enabled?

  #368 opened 5 months ago by SKRohit
  0

• Orbit Motion of camera in Image to video

  #365 opened 6 months ago by Smartauto
  0

• Plans for UnClipXL

  #363 opened 6 months ago by belgai
  0

• A Driving World Model based on SVD (incl. all training code)

  #362 opened 6 months ago by Little-Podi
  0

• DiffusionEngine miss 'test_step' define

  #359 opened 6 months ago by zhangxingmeng
  1

• Is anyone trying to train their own SVD-based Camera Motion LoRA model?

  #357 opened 6 months ago by DataAIPlayer
  5

• Classifier Free Guidance for StableVideoDiffusion

  #358 opened 6 months ago by tykim0507
  0