Giters
Stability-AI
/
generative-models
Generative Models by Stability AI
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
22915
Watchers:
248
Issues:
267
Forks:
2523
Stability-AI/generative-models Issues
During the training process of the Diffusion model, a stable Loss cannot be obtained, and images cannot be generated at all times.
Updated
3 months ago
Barber
Updated
a month ago
Comments count
1
ModuleNotFoundError: No module named 'scripts'
Updated
3 months ago
Comments count
1
while running infrence
Updated
3 months ago
sample by svd: No module named 'scripts.util'
Updated
3 months ago
Comments count
2
1
Updated
3 months ago
ModuleNotFoundError: No module named 'scripts'
Closed
3 months ago
motion_bucket_id samples from each bucket
Updated
3 months ago
FileNotFoundError: No such file or directory: "checkpoints/svd.safetensors"
Updated
3 months ago
Comments count
4
Finetune SVD with discrete time noise sampler
Updated
4 months ago
sampling.py returns dead
Updated
3 months ago
Comments count
2
where should I put the sd_xl_base.yaml?
Updated
4 months ago
Comments count
1
Already known black images generation with some GC
Updated
4 months ago
Am I the only one getting this issue?
Updated
2 months ago
Comments count
3
What kind of GPU do you use to train svd_xt with 1024x576 resolution and 25 frames.
Updated
a month ago
Comments count
2
Finetuning SVD with right fps_id and motion_bucket_id values
Updated
4 months ago
Stable
Updated
4 months ago
Turbo SD with PLMS samples
Updated
5 months ago
Training code for ADD
Updated
5 months ago
Training objective function of SVD.
Closed
5 months ago
Error while running SVD-Series with CPU
Updated
3 months ago
Comments count
1
Cannot install on Debian 12. It says "error: casting `&T` to `&mut T` is undefined behavior" during requirements installation.
Closed
5 months ago
Comments count
2
any webui for the great project ?
Updated
5 months ago
Positional encoding for time for temporal attention layers in SVD
Updated
5 months ago
Comments count
1
Sampling with EulerEDMSampler for 31 steps: 0%|
Updated
5 months ago
Comments count
2
[Feature] Stable Video Diffusion Training Code
Updated
a month ago
Comments count
1
Video-to-Video Translation via Stable-Video-Diffusion?
Updated
5 months ago
[BUG]The following bugs have appeared in 'img2img'
Updated
3 months ago
Comments count
1
[Question] SVD/SVD-XT performance on older GPU (i.e. without Triton support)
Updated
5 months ago
Comments count
1
r
Closed
5 months ago
Blank
Closed
5 months ago
Where is the downloaded model stored?
Updated
4 months ago
Comments count
1
omegaconf.errors.ConfigAttributeError: Missing key sampler_config
Updated
5 months ago
much higher COCO fid_5k score than ADD paper
Updated
6 months ago
UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd7 in position 373: invalid continuation byte
Updated
6 months ago
package versions have conflicting dependencies
Updated
6 months ago
OOM when loading SDXL-turbo
Updated
6 months ago
[BUG]The use of refiner1.0 in SDXL 1.0 will result in errors(txt2img-images).
Updated
6 months ago
Request for pure CLI txt2img.py
Updated
6 months ago
No “test_step()” method defined to run `Trainer.test`.
Updated
5 months ago
Comments count
4
train SVD XT
Updated
5 months ago
Comments count
4
[Stable Video Diffusion] How to increase the motion of the video by adjusting the parameter
Updated
6 months ago
Comments count
1
[Stable Video Diffusion] first frame is not equal to initial image
Updated
5 months ago
Comments count
5
question of ADD(Adversarial Diffusion Distillation), the inputs of teacher nets
Updated
5 months ago
Comments count
4
Will the text-to-video model be released?
Updated
5 months ago
Comments count
1
What kind of LLM do you use and what the prompt do you provide to LLM?
Updated
6 months ago
First Stage Decoder Error
Updated
6 months ago
OutOfMemoryError: CUDA out of memory.
Updated
6 months ago
How to train Stable Video Diffusion model?
Updated
a month ago
Comments count
10
Training code for the Adversarial Diffusion Distillation(ADD) not available?
Updated
3 months ago
Comments count
19
Previous
Next