What are the stable cascade limitations? Has anyone used it
What are the stable cascade limitations? Has anyone used it
Fnot much yet
Fbut it is getting added slowly
Fto trainers
UChatMusician
Understanding and Generating Music Intrinsically with LLM
While Large Language Models (LLMs) demonstrate impressive capabilities in text generation, we find that their ability has yet to be generalized to music, humanity's creative language. We introduce…
Understanding and Generating Music Intrinsically with LLM
While Large Language Models (LLMs) demonstrate impressive capabilities in text generation, we find that their ability has yet to be generalized to music, humanity's creative language. We introduce…
2/27/24, 4:51 AM
Udid you see this
Fno first time seeing
UPlayground v2.5 Gradio apps are out
Model claims outperforming SDXL, DALL-E 3 & Midjourney 5.2!
Focus on aesthetic quality, enhanced colors & contrast
Generation for multi-aspect ratios
Improved human-centric fine detail.
Model claims outperforming SDXL, DALL-E 3 & Midjourney 5.2!
Focus on aesthetic quality, enhanced colors & contrast
Generation for multi-aspect ratiosImproved human-centric fine detail.
2/27/24, 7:20 PM
UNew Playground version
UI cannot keep up with the AI news anymore. So much happening these days.
F:d
Fi tested to train on 2
Fbut it didnt yield good
Fneed new research parameters
UI tried 2 also and didn't like it but maybe 2.5 is better.
AEMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
Fye started following
Fbut no hopes they will release
AThis upscaling is 100% local isn't it? It seems like it's dramatically slowed down for some reason
ADoctor did you make this interface for this upscaler?
Fyes 100% local
Fi used the demo they published
AHi All, I'm trying to get Supir running but I am getting this error, with all updates of I have tried, any thoughts?
BI'm currently experimenting with SUPIR for batch converting video frames into images. However, when the images are exported to a folder, they're labeled with the processing time instead of the frame order, which makes it challenging to reassemble the frames correctly. Is there a way to ensure the images are exported in the proper sequence?
BOr at least have the processed image, the same file name as the input image (just in a different folder)
Fhi yes python version error
Fplease install with python 3.10.11
Fvery accurate
Ftoday hopefully i am going to fix this issue
Fi plan to make like
Finput_image_name_00001.png and so on
BYeah that would be great!
BI'm currently using runpod to test, whats the fasted GPU for SUPIR upscaling?
Fprobably A6000 and above
Fi mean if you dont use optimizations it will be faster
BOk great
BI tried the A6000 before but ran out of memory without optimisations
Fin that case
Fyou can enable optimizations and upscale bigger
For you can get A100 with 80GB
Bok will do thats
B*thanks
Fyou are welcome
EFor SUPIR_v13, do we need to reinstall or just git pull?
EAlso can you make a tutorial on what each parameter settings do? Or share best settings you've tested.
EAlso, the Terms of use in the Gradio UI says it's no-commercial use. But the license of SUPIR on Github is MIT open-source License. Is it no-commercial use?
ARoger that, thank you!
BI've been trying this new SUPIR from the Patreon and haven't been able to upscale a single image... It takes forever even on my 4090 and then stalls out each time.
B[Tiled VAE]: Executing Encoder Task Queue: 100%|█████████████████████████████████| 17472/17472 [00:56<00:00, 308.84it/s]
[Tiled VAE]: Done in 57.083s, max VRAM alloc 10934.813 MB
C:\Users\xxxx\Deep\SUPIR\SUPIR\venv\lib\site-packages\torch\nn\functional.py:5476: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:263.)
attn_output = scaled_dot_product_attention(q, k, v, attn_mask, dropout_p, is_causal)
[Tiled VAE]: Done in 57.083s, max VRAM alloc 10934.813 MB
C:\Users\xxxx\Deep\SUPIR\SUPIR\venv\lib\site-packages\torch\nn\functional.py:5476: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:263.)
attn_output = scaled_dot_product_attention(q, k, v, attn_mask, dropout_p, is_causal)
![Dazzastrous [4090]](https://cdn.discordapp.com/avatars/871389071686135838/c4a5f4d81d9eeb18d856295d692e2c07.webp?size=40)
Dhow big is your input image
Dmight be too high resolution