Software Engineering Courses (SECourses)•2y ago

Also, the Terms of use in the Gradio UI says it's no-commercial use. But the license of SUPIR on Git

Also, 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?

FFurkan Gözükara SECourses hi yes python version error

andrew.beniston•2/28/24, 5:10 PM

Roger that, thank you!

BecauseReasons•2/28/24, 6:04 PM

I'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.

BecauseReasons•2/28/24, 6:04 PM

[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)

Dazzastrous [4090]•2/28/24, 6:05 PM

how big is your input image

Dazzastrous [4090]•2/28/24, 6:05 PM

might be too high resolution

BecauseReasons•2/28/24, 6:30 PM

3072x4080

BecauseReasons•2/28/24, 6:30 PM

Too big?

Dazzastrous [4090]•2/28/24, 6:30 PM

yup

Dazzastrous [4090]•2/28/24, 6:31 PM

thats the sort of resolution you want to be upscaling too

huy trần•2/28/24, 6:55 PM

when try install one click , i got error : Traceback (most recent call last):
File "X:\03_General\huy\supir\SUPIR\gradio_demo.py", line 5, in <module>
from gradio_imageslider import ImageSlider
File "C:\Users\AZPC\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio_imageslider__init__.py", line 1, in <module>
from .imageslider import ImageSlider
File "C:\Users\AZPC\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio_imageslider\imageslider.py", line 16, in <module>
from gradio.events import Events
ImportError: cannot import name 'Events' from 'gradio.events' (C:\Users\AZPC\AppData\Local\Programs\Python\Python310\lib\site-packages\gradio\events.py)
Press any key to continue . . .

BBecauseReasons 3072x4080

B0nd•2/28/24, 7:42 PM

Yeah that’s way too big. SUPIR shines with really small images

FFurkan Gözükara SECourses you are welcome

B0nd•2/28/24, 7:42 PM

Do you have any tips to help improve consistency between images, when batch upscaling?

Dazzastrous [4090]•2/28/24, 11:56 PM

Ideogram 1.0 , text is really good along with prompt following, kinda like SD3 but released now

AIGambino•2/29/24, 12:14 AM

Has anyone manually installed supir?

AIGambino•2/29/24, 12:41 AM

I'm a bit lost at this point
For users who can connect to huggingface, please setting LLAVA_CLIP_PATH, SDXL_CLIP1_PATH, SDXL_CLIP2_CKPT_PTH in CKPT_PTH.py as None. These CLIPs will be downloaded automatically.

ErikOP•2/29/24, 10:07 AM

I used ChatGPT to explain some new parameters in SUPIR:
--edm_steps: Number of steps for the EDM Sampling Scheduler. This determines how many iterations the sampling process will take. A higher number generally means more refinement but takes longer.

--s_stage1: Strength control for the first stage of processing. A negative value indicates that this stage is not used.

--s_churn: A hyperparameter of the EDM process, influencing the variability or diversity in the generated samples.

--s_noise: Another hyperparameter for EDM, affecting the amount of noise introduced during the diffusion process, which can impact the clarity or smoothness of the output.

--s_cfg: Classifier-free guidance scale for prompts. This parameter adjusts the influence of textual prompts on the generation process, affecting how closely the output matches the given textual description.

--s_stage2: Strength control for the second stage of processing. Adjusts the intensity of modifications in the second stage.

linear_CFG and --linear_s_stage2: These settings allow for a linear increase of the s_cfg and s_stage2 parameters from their start points (--spt_linear_CFG and --spt_linear_s_stage2) to their specified values through the process, providing a way to dynamically adjust the guidance strength.

--spt_linear_CFG and --spt_linear_s_stage2: Define the starting points for the linear increase of s_cfg and s_stage2, respectively.

--ae_dtype and --diff_dtype: Specify the data types (precision) used during inference for the autoencoder and diffusion processes, respectively, affecting memory usage and computational speed.

EErik Also, the Terms of use in the Gradio UI says it's no-commercial use. But the lic...

Furkan Gözükara SECourses•2/29/24, 8:35 PM

i think if you dont make a SaaS out of it they wont care

EErik For SUPIR_v13, do we need to reinstall or just git pull?

Furkan Gözükara SECourses•2/29/24, 8:35 PM

just git pull

ErikOP•2/29/24, 8:35 PM

Cool

BBecauseReasons 3072x4080

Furkan Gözükara SECourses•2/29/24, 8:36 PM

yes too big

Hhuy trần when try install one click , i got error : Traceback (most recent call last): ...

Furkan Gözükara SECourses•2/29/24, 8:36 PM

hello. when you were installing did you see any error on cmd?

Furkan Gözükara SECourses•2/29/24, 8:37 PM

can you reinstall into a new folder and share entire install cmd logs with me?

Deleted User•2/29/24, 10:18 PM

@Furkan Gözükara SECourses do you know how to make SUPIR work on ComfyUI with reduced memory? I’ve been trying to run the ComfyUI node but it runs out of VRAM - I’m using Colab T4 which has 15gb of VRAM

DDeleted User <@205854764540362752> do you know how to make SUPIR work on ComfyUI with reduced...

Furkan Gözükara SECourses•2/29/24, 10:47 PM

sadly no idea

Furkan Gözükara SECourses•2/29/24, 10:47 PM

i am not really expert at comfyui

FFurkan Gözükara SECourses sadly no idea

Deleted User•2/29/24, 10:47 PM

What is it that you changed on your version? Is it that you’re loading the SUPIR models as fp16 instead? Is that what the half weights thing is?

DDeleted User What is it that you changed on your version? Is it that you’re loading the SUPIR...

Furkan Gözükara SECourses•2/29/24, 10:48 PM

we changed SUPIR model weights precision

Furkan Gözükara SECourses•2/29/24, 10:49 PM

and added tiled VAE

Furkan Gözükara SECourses•2/29/24, 10:49 PM

both from official repo

FFurkan Gözükara SECourses we changed SUPIR model weights precision

Deleted User•2/29/24, 10:50 PM

From FP32 -> FP16?

DDeleted User From FP32 -> FP16?

Furkan Gözükara SECourses•2/29/24, 10:58 PM

yep

Furkan Gözükara SECourses•2/29/24, 10:58 PM

half

barepixels•3/1/24, 2:47 AM

Just FYI, I upscale a pano 2048x1024 to 4096x2048 (2x) and it was eating over 20 gigs of Vram. That's the limit my 3090 can do. It did add a lot of details. Some area didn't look good so I did another version of 2x with Topaz Gigapixels. I then cherry pick masked in area I like best from the two with Photoshop. You can see the final pano here "https://sapphiregreenearth.com/stabledifussionwaterfall2/"

Thinking back, maybe Magnific can be justified for their high price, considering the amount of Vram they need time the amount of servers they use.

Sapphire Green Earthstaff

Top Green, Natural and Organic Products | Sapphire Green Earth

Sapphire Green Earth is dedicated to creating a convenient and affordable path to the use of top green , natural and organic products.

Bbarepixels Just FYI, I upscale a pano 2048x1024 to 4096x2048 (2x) and it was eating over 20...

Furkan Gözükara SECourses•3/1/24, 2:58 AM

nice pic

AIGambino•3/1/24, 3:07 AM

Deepfaking the young rock tv show actor into actual Dwayne Johnson haha