(All lesson resources are available at http://course.fast.ai.) This is the first lesson of part 2 of Practical Deep Learning for Coders. It starts with a tutorial on how to use pipelines in the Diffusers library to generate images. Diffusers is (in our opinion!) the best library available at the moment for image generation. It has many features and is very flexible. We explain how to use its many features, and discuss options for accessing the GPU resources needed to use the library.

We talk about some of the nifty tweaks available when using Stable Diffusion in Diffusers, and show how to use them: guidance scale (for varying the amount the prompt is used), negative prompts (for removing concepts from an image), image initialisation (for starting with an existing image), textual inversion (for adding your own concepts to generated images), Dreambooth (an alternative approach to textual inversion).

The second half of the lesson covers the key concepts involved in Stable Diffusion:
- CLIP embeddings
- The VAE (variational autoencoder)
- Predicting noise with the unet
- Removing noise with schedulers.

You can discuss this lesson, and access links to all notebooks and resources from it, at this forum topic: https://forums.fast.ai/t/lesso....n-9-part-2-preview/1

0:00 - Introduction
6:38 - This course vs DALL-E 2
10:38 - How to take full advantage of this course
12:14 - Cloud computing options
14:58 - Getting started (Github, notebooks to play with, resources)
20:48 - Diffusion notebook from Hugging Face
26:59 - How stable diffusion works
30:06 - Diffusion notebook (guidance scale, negative prompts, init image, textual inversion, Dreambooth)
45:00 - Stable diffusion explained
53:04 - Math notation correction
1:14:37 - Creating a neural network to predict noise in an image
1:27:46 - Working with images and compressing the data with autoencoders
1:40:12 - Explaining latents that will be input into the unet
1:43:54 - Adding text as one hot encoded input to the noise and drawing (aka guidance)
1:47:06 - How to represent numbers vs text embeddings in our model with CLIP encoders
1:53:13 - CLIP encoder loss function
2:00:55 - Caveat regarding "time steps"
2:07:04 Why don’t we do this all in one step?

Thanks to fmussari for the transcript, and to Raymond-Wu (on forums.fast.ai) for the timestamps.

If you're looking for an easy method to create consistent characters within Stable Diffusion, then look no further than this Stable Diffusion tutorial. You will learn a prompt based method for achieving consistency. This includes prompting techniques to get the results you want. Best of all, this method does not include complex tools to learn.

Support the Channel:
➤ Patreon: https://www.patreon.com/BitesizedGenius
➤ Buy Me Coffee: https://bmc.link/bitesizedgenius
➤ Tutorials: https://www.bitesizedgenius.com/

Links:
➤ Prompting Techniques: https://youtu.be/dlUpSEbbCho
➤ More Prompting Techniques: https://youtu.be/UeR0yZOYS0Y
➤ Where Files Go: https://youtu.be/FDOEhgpravM
➤ Checkpoint: https://civitai.com/models/81458/absolutereality
➤ Upscalers: https://huggingface.co/uwg/ups....caler/tree/main/ESRG
➤ Instant Photo Lora: https://civitai.com/models/526....52/leosams-instant-p
➤ Dark Light Lora: https://civitai.com/models/147....751?modelVersionId=1
➤ Bad/Unrealistic Dream Embedding: https://civitai.com/models/724....37?modelVersionId=77
➤ MSE-840000 VAE: https://huggingface.co/stabili....tyai/sd-vae-ft-mse-o
➤ Anything V3 VAE: https://huggingface.co/Linaqru....f/anything-v3.0/blob
➤ KL-F8 VAE: https://huggingface.co/hakurei..../waifu-diffusion-v1-

Chapters
0:00 - Introduction
0:48 - Prerequisites
2:04 - Names Impact Faces
3:24 - Promoting Techniques
6:41 - Image Editing
7:20 - Conclusion

Part 1: Install Stable Diffusion https://youtu.be/kqXpAKVQDNU
In this Stable Diffusion tutorial we'll go through the basics of generative AI art and how to generate your first images. Chat with me in our community discord: https://discord.gg/dFB7zuXyFY
Thank me on Patreon so I can keep making these videos https://www.patreon.com/sebastiankamph

Prompt styles here:
https://www.patreon.com/posts/sebs-hilis-79649068

Check out sponsor RunDiffusion here: https://app.rundiffusion.com/?ref=sebastian91
Use promo code: sebastiankamph15 for 15% off Creator's Club. Stable Diffusion in the cloud.

NMKD Siax 4x upscaler model: https://icedrive.net/s/43GNBihZyi
Place inside stable-diffusion-webui\models\ESRGAN\

Support me on Patreon and make me happy! https://www.patreon.com/sebastiankamph

Chat with me in our community discord: https://discord.gg/dFB7zuXyFY

My Weekly AI Art Challenges https://www.youtube.com/playli....st?list=PLXS4AwfYDUi

My Stable diffusion workflow to Perfect Images https://youtu.be/4u-Ytioi3DM

ControlNet tutorial and install guide https://youtu.be/vFZgPyCJflE

Famous Scenes Remade by ControlNet AI https://youtu.be/wVbWZ-Ph9lE

LIVE Pose in Stable Diffusion https://youtu.be/uAI_FBK6UPc

Control Lights in Stable Diffusion https://youtu.be/_xHC3bT5GBU

Ultimate Stable diffusion guide https://youtu.be/DHaL56P6f5M

Inpainting Tutorial - Stable Diffusion https://youtu.be/No1_sq-i_5U

The Rise of AI Art: A Creative Revolution https://youtu.be/Ujpr62w7qcU

7 Secrets to writing with ChatGPT (Don't tell your boss!) https://youtu.be/G5pld_ELBI0

Ultimate Animation guide in Stable diffusion https://youtu.be/lztn6qLc9UE

Dreambooth tutorial for Stable diffusion https://youtu.be/Z-hyKADmHmE

5 tricks you're not using in Stable diffusion https://youtu.be/-5TaeHvnVxE

Avoid these 7 mistakes in Stable diffusion https://youtu.be/b8xWjrzTAPY

How to ChatGPT. ChatGPT explained in 1 minute https://youtu.be/APvEaj19Io4

This is Adobe Firefly. AI For Professionals https://youtu.be/TInvekF6NRw

Adobe Firefly Tutorial https://youtu.be/ifnAjKiMVaU

ChatGPT Playlist https://www.youtube.com/playli....st?list=PLXS4AwfYDUi

CHAPTERS
0:00 Welcome to Stable Diffusion
2:21 Text2img
12:10 Sponsor & Dadjoke
13:46 Hiresfix
15:47 More Text2img
16:49 ControlNet Lite
18:05 Img2img
22:45 Inpaint Lite
24:27 Extras/Upscaler
26:14 Png Info

Learn how to use Stable Diffusion to create art and images in this full course. You will learn how to train your own model, how to use Control Net, how to use Stable Diffusion's API endpoint, and more.

The ethical implications of AI in art are significant. This course aims to educate on the technical aspects of the tool. We emphasize the importance of using it responsibly and respecting the rights of artists.

✏️ Course created by @lynnzheng

🔗 Install stable diffusion: https://github.com/AUTOMATIC11....11/stable-diffusion-
🔗 Download models: https://civitai.com/
🔗 Download VAE for Model "Counterfeit": https://huggingface.co/gsdf/Co....unterfeit-V2.5/blob/
🔗 Download Embeddings: https://huggingface.co/datasets/gsdf/EasyNegative
🔗 Train a Lora: https://civitai.com/models/22530
🔗 Install Control Net - https://github.com/Mikubill/sd-webui-controlnet
(Use --enable-insecure-extension-access extensions)

🎉 Thanks to our Champion and Sponsor supporters:
👾 davthecoder
👾 jedi-or-sith
👾 南宮千影
👾 Agustín Kussrow
👾 Nattira Maneerat
👾 Heather Wcislo
👾 Serhiy Kalinets
👾 Justin Hual
👾 Otis Morgan

--

Learn to code for free and get a developer job: https://www.freecodecamp.org

Read hundreds of articles on programming: https://freecodecamp.org/news

A mostly unattended generative piece on the eurorack, just letting this one run.

This patch only uses 4 main voices. 4ms Ensemble (Vangelis brass), MI Plaits (Synth parts), 2xAcid Rain Chainsaws (Bass and partial chords). Plus, a loop via Lubadh (improvised recording from Wavestate) and the background noise/traffic sample.

#ambientmusic #relaxingmusic #meditationmusic
Patch Notes:

Main clock from Pamela's New Workout, into Ladik R-110 for the random trigs/gates which are essential to this patch.

(Synth voice - Plaits)Trig 1 goes through a Ladik S-090 Skipper at around 60%, which also is being CV modulated via Modbox with a very slow LFO. Trig 1 is then sent to Sinfonion Arp Clock input, which is also copied out to Delta V envelope generator slow atk/decay (decay modulated gently via one of Ochd's outputs). This envelope controls Plaits output via the built into VCA in Delta V. Sinfonion Arp 1v/Oct Out goes into Plaits (arp set to either random or Brownian). Plaits Timbre is modulated via URA A-Out, Harm by B-Out, and Morph by another channel of Ochd. Plaits also receives fast sine LFO FM for vibrato. Plaits then goes through Belgrad, with v/oct modulated by second channel of Delta V 50%atk, 50%dcy (same Trig 1 activates it), which is also copied to Ochd CV input to modulated Ochd speed everytime the envelope is triggered. Belgrad set to 6th filter, FM on, 60% resonance. Span modulated via slow LFO of Ochd, and FM modulated by fast LFO of Ochd.

(Vangelis lead - 4ms Ensemble) Gate1 from Ladik R-110 into Skipper set around 50% (CV modulated) via slow LFO from Modbox. Output from Skipper goes to Quadigy channel 1 and copied to Trig input on RndStep, copied again to Time Warp Gate input. Quadigy Ch.1 Envelope to Tallin linear input, slow attack/decay. Input into Tallin 4ms Ensemble Out B, Balance set to 70%, Twist, Warp and Cross FM all at 0%. Twist opens up via Ch.2 of Quadigy which is tied to Ch.1's trigger, and also has a slow atk/decay for the synth swell. RndStep Bipolar output (attentuated) goes to Ch.3 on Sinfonion, with Ch.3 Sin output going into Time Warp (for Slew), out from Time Warp into 4ms Ensemble 1v/oct input.

(Chainsaw Bass) Ch.1 Output from Sinfonion provides notes, into Chainsaw 1v/oct input. Chainsaw then into Freak filter (Steiner-Parker model), cutoff modulated via Ch. 4 of Quadigy which is triggered by PNW very slow/divided pulse into Skipper.

(Chainsaw 2-note chords) Sinfonion chord Out 1 and Out 3 to second Chainsaw, then out to dual Cinnamon filters set to low-pass, with soft/slow LFO over cutoff via Batumi.

(Sinfonion Key Change) Sinfonion song set to just two steps = E7 to A Major. In1 on Sinfonion set to advance through steps via Trig. Trig comes from PNW slow/heavily divided gate into another Skipper, then to Sinfonion.

Lubadh plays back improvised recording from the Wavestate.

My rack on Modular Grid (updated on 6/12/20): https://www.modulargrid.net/e/racks/view/1138978

Recorded direct to DAW


Please like and subscribe if you enjoyed the music, and want to be notified of new uploads.

----------------------------------------------------------

▬ Subscribe for more videos ► http://bit.ly/2EnqQfq

▬ Follow me on Soundcloud ► http://bit.ly/2DL90pn

▬ State Azure on Bandcamp ► http://bit.ly/2BztXh3

▬ Follow me on Facebook ► http://bit.ly/2ElMz7h

▬ Follow me on Instagram ► https://bit.ly/2wXqloS

▬ Follow me on Spotify ► https://spoti.fi/2ATRDPq

#modularsynth
#eurorack
#stateazure

Sledgehammer AI Music Video by Kush
Placed in the Top 10 as Finalist for StabilityAI's DiffuseTogether Contest.
I used a combination of spreadsheets and Stability Diffusion tools as well was Warp Fusion to create this video.
Insta: https://www.instagram.com/metamushrooms/
Twitter: https://twitter.com/MetaMushrooms
Available for commissions.
#musicvideo #petergabriel #psychedelic #aimusicvideo #aivideo

--
This video was created using a spreadsheet and Stability AI tools for the DiffuseTogether competition featuring the music of Peter Gabriel.
#stablediffusion #stabilityai #petergabriel #musicvideo
--
Peter Gabriel had always been ahead of his time when it came to music. He had always pushed the boundaries and experimented with new sounds, but as he aged, he realized that his time in the spotlight was limited. He wanted to find a way to continue his music long after his physical body gave up on him. That's when he discovered the Metaverse.

The Metaverse was a virtual world where people could exist as digital beings. It was a place where one's consciousness could be uploaded and one could exist forever in a virtual world. Peter Gabriel saw this as the perfect opportunity to continue his music career long after his physical body had deteriorated. He began working on a project that would allow him to upload his consciousness into the Metaverse and transform himself into a cyborg performer.

Using advanced AI and spare parts, Peter Gabriel worked tirelessly to create the perfect cyborg version of himself. He called it the "Sledgehammer," after his hit song. As he worked, he couldn't help but think of the lyrics to the song, "I kicked the habit. Shed my skin." He was shedding his physical body and becoming something new, something immortal.

Finally, after months of hard work, the Sledgehammer was complete. Peter Gabriel uploaded his consciousness into the cyborg body and emerged as a digital being. He was no longer bound by the limitations of his physical body, and he could perform his music for eternity. As he took to the virtual stage, he sang the lyrics to "Sledgehammer," his metaphor for his transformation into a cyborg performer.

"I'm your Sledgehammer. Let there be no doubt about it." Peter Gabriel was now a force to be reckoned with in the virtual world, a performer that would never tire or grow old. "I've kicked the habit. Shed my skin. This is the new stuff. I go dancing in." He was dancing in the Metaverse, free to perform his music for all eternity.

As the concert came to an end, Peter Gabriel felt a sense of satisfaction that he had never felt before. He had achieved immortality through his music, and he knew that his legacy would live on long after he was gone. "You could have a steam train. If you'd just lay down your tracks." Peter Gabriel had laid down his tracks, and now he would ride the steam train of his music into eternity.

Relax by the pool and soak in the the calming water sounds in this exotic tropical swimming pool in the rainforest. Beautiful 4K ambience for for home, work or a spa. Display on your TV for a gorgeous background.

For a long time, I have been struggling with sleepless nights, tossing and turning as the minutes and hours ticked by. My mind races with thoughts and worries, making it nearly impossible to find the peaceful sleep I desperately need. This constant battle with insomnia has always left me feeling fatigued and frustrated, searching for ways to improve my sleep and reclaim a sense of normalcy in my daily life.

I have experimented with nearly every solution to enhance my sleep. Ultimately, I've discovered five devices that have significantly elevated my quality of my rest.

Sleep Tracker - https://amzn.to/3FC2mji
Sleep Mask - https://amzn.to/3LJCANI
Mouth Tape - https://amzn.to/3lq4ZxE
Bluelight Blockers - https://amzn.to/3Z2qLpd
Noise Machine - https://amzn.to/3n1ZWUG

Thank you for watching and don't forget to subscribe!

Ai generated kid playing Kalimba

Welcome to a cyberpunk-inspired world of deep focus and relaxation. Our handpicked selection of futuristic tunes is tailored for programmers, dreamers, and visionaries. 🚀🎶

🌆 Immerse yourself in the neon-lit cityscape and let the calming beats guide your thoughts. This music is designed to be your digital companion in your journey through lines of code and moments of creative clarity.

🤖 Unleash your productivity with our carefully curated mix, perfect for coding, designing, or just unwinding after a long day of tech wizardry. As the day transforms into night, let this music transport you to the realm of cybernetic dreams.

⌨️ Whether you're debugging code or simply need a mental escape, our cyberpunk sounds will provide the perfect atmosphere. The fusion of technology and music comes alive in this playlist, crafted to enhance your focus and encourage relaxation.

Get ready to code, create, and unwind in a style that only the cyberpunk world can provide. Press play, and let your imagination roam through futuristic streets and virtual landscapes.

Turn up the volume and dive into the future. 🌃

If you enjoyed this video like, comment or subscribe to the channel. 🙏
Join our English-speaking Discord to get in contact with us and fellow music lovers. ❤️
https://discord.gg/5p8D8GdVfp

Genre: Electronic music
Style: Chillout, Chillstep
Mood: Rainy, Night, Dark
Feature: Without Lyrics

📹 Similar videos
► https://www.youtube.com/playli....st?list=PLdE7uo_7KBk
► https://www.youtube.com/playli....st?list=PLdE7uo_7KBk
► https://www.youtube.com/playli....st?list=PLdE7uo_7KBk
► https://www.youtube.com/playli....st?list=PLdE7uo_7KBk
► https://www.youtube.com/playli....st?list=PLdE7uo_7KBk
► https://www.youtube.com/playli....st?list=PLdE7uo_7KBk

🎧 Tracklist
► 00:00 Vonnboyd - Discover
► 03:50 Honeyruin - We Could Have Been
► 07:46 Blurred, Heartmath2 - Dawning (Creepa Remix)
► 12:19 Andy Leech - Solar Fields
► 17:09 AK - 23.01.2018
► 20:34 VonnBoyd - Broken Heart
► 26:08 AK - Autumn Is Here
► 29:38 Koda - Staying
► 33:56 Tim Schaufert, AK - From Place Еo Place
► 36:57 AK - Wanderlust
► 40:38 4Lienetic - The Fog Ahead
► 45:05 Hands - Thinking About You
► 48:20 H3ndo - Fathom
► 53:43 Arnyd - Truth
► 57:25 Ambient Light - Norwegian Valley
► 1:00:56 Ponkie - Falling Stars
► 1:04:36 Randloev - Patience
► 1:09:08 Artic Desert - Enigma
► 1:12:49 Many Miles - Look Down
► 1:16:45 Onycs - Timeless
► 1:20:58 Samuke - Haze
► 1:23:51 Homeomorphic - Imaginary
► 1:26:53 Kasper Klick - Salvation
► 1:31:14 Homeomorphic - Awareness
► 1:34:52 Bythewvve - Return
► 1:37:54 Rusez1 - Aftermath


#CyberpunkChill #FocusMusic #RelaxationBeats

⁣In the warm embrace of sunrise, a tiny turtle emerged from its sandy nest. It was the beginning of a perilous adventure. Guided by an instinctual calling, the young hatchling embarked on a journey, where darkness and uncertainty lay ahead.

How to install Stable Diffusion on your local PC: https://youtu.be/TbLAtMN7Vyk
How to install ControlNet in Stable Diffusion: https://youtu.be/oO3zIfH4LRE
Roop extension on GitHub: https://github.com/s0md3v/sd-webui-roop/

Very impressive AI driving image and video upscale https://topazlabs.com/ref/1514/ , try for free.
THANK YOU for your support!
Please subscribe and leave your comments, and don't forget to click on the notification bell: “Look daddy, the teacher says, every time a bell rings an angel gets his wings,” ZuZu Bailey from “It's A Wonderful Life.”

What do I use:
Image upscaling https://topazlabs.com/ref/1514/
Micro SD cards 256Gb V3, I use these in Drones, Insta 360, and GoPro's https://amzn.to/3HsTU7j
Must have: Micro SD storage/reader/Cables: https://amzn.to/3GZ33D8
Simplified Photoshop, no annual fees, just one-time purchase https://amzn.to/3DaUpAi
Canon R5 is not cheap, but it is definitely the best https://amzn.to/3DclTFX
Must have lens adapter EF to RF https://amzn.to/3Dk1qhp
Insta 360 X3, I am really impressed by this camera: https://amzn.to/3HqdMb4
My to-go camera GoPro 11 : https://amzn.to/3XMcKMc
DJI Osmo 6 https://amzn.to/3zsKlAG
Portable lights, very versatile usage : https://amzn.to/3wsUqMa
Another DJI great product. Drone Mini 3 Pro, my togo: https://amzn.to/3XKN9mG
One of my favorite modifiers from Fotodiox - https://amzn.to/2Rfr1Px
Another modifier, that helps with fill light - https://amzn.to/2ReC2jX
Corsair keyboard: https://amzn.to/3DlclHN
Adobe Photoshop CC - https://amzn.to/2TNrLwL

My #1 dress in Baroque/Rococo photoshoots. very good quality: https://amzn.to/401rGHQ
Baroque outfit for males: https://amzn.to/3kBdEg2
I recommend getting this shirt for the outfit above: https://amzn.to/3Wzcv5Z

My Vue book - https://amzn.to/2TGUkvQ
3D Art essentials - https://amzn.to/2RfqPjh

My Patreon webpage - https://www.patreon.com/geekatplay
Tutorials and packs - https://gumroad.com/geekatplay
Tutorials website - https://www.geekatplay.com
Photography - https://www.chopinephotography.com

Subscribe to my channel for fast notifications on new tutorials - https://www.youtube.com/@geekatplay

Stable Audio is ready to roar! Try out our new AI product for music and sound generation now!

With Stable Audio, you can generate music or sound effects from a text prompt and a specified duration. It uses a latent diffusion for audio model to generate audio in high-quality, 44.1 kHz stereo. Pro users can download the audio for commercial use - but it's free for everyone to try.

Please share your creations and tag us! www.stableaudio.com

Update:
If you want to use the non standard model for 1.5 training then you can grab the name form hugging space such as XpucT/Deliberate, and use the word 'main" for the branch.

Instead of putting the trigger word in for the class you can use instead like "photo of a man" or "photo of a person" I've had better results with that.

I still recommend 1600 steps

This is the easiest way to train an AI model with or without a GUI for Stable Diffusion.

I wanted to try a similar thumbnail to Aitrepreneur as I really love the way they do thumbnails.

https://stable-diffusion-art.com/dreambooth/
https://www.birme.net/

https://colab.research.google.....com/github/sagiodev/

Other Great Resources:
https://www.youtube.com/@Aitrepreneur
https://www.youtube.com/@NerdyRodent
https://www.youtube.com/@enigmatic_e
https://www.youtube.com/@TutorialsAI

► Boosty (эксклюзив) ➜ https://boosty.to/xpuct
► Telegram ➜ https://t.me/win10tweaker
► Discord ➜ https://discord.gg/xpuct

Stable Video Diffusion:
https://github.com/Stability-AI/generative-models

🔥 Deliberate: https://huggingface.co/XpucT/Deliberate/tree/main
🔥 Reliberate: https://huggingface.co/XpucT/Reliberate/tree/main
🔥 LowRA: https://huggingface.co/XpucT/Loras/tree/main

Плейлист Stable Diffusion: https://www.youtube.com/playli....st?list=PL05SB3rBbUs
МОЯ ВЕРСИЯ Stable Diffusion: https://youtu.be/jepK6ufemMw

#StableDiffusion #StableVideoDiffusion

The Reliberate Model is insanely good. It's hosted on CivitAI. This Stable Diffusion Model is for A1111, Vlad Diffusion, Invoke and more. It can create extrem details in upscaled images. In this Video I show you how to get the most out of it. I combine it with the LowRA Lora and the Detail Tweaker Lora to get even more Details from the Upscale. We are also going to use the SD Uscale Script with the Ultrasharp Model to get the best and highest details from this Model.

#### links from the Video ####
Detail Tweaker Tutorial: https://youtu.be/DMFP8ZHb5-8
Ultrasharp Tutorial: https://youtu.be/A6dQPMy_tHY
Reliberate Model: https://civitai.com/models/79754/reliberate
LowRA Lora: https://civitai.com/models/48139/lowra
Detail Tweaker Lora: https://civitai.com/models/583....90/detail-tweaker-lo

#### Join and Support me ####
Buy me a Coffee: https://www.buymeacoffee.com/oliviotutorials
Join my Facebook Group: https://www.facebook.com/groups/theairevolution
Joint my Discord Group: https://discord.gg/XKAk7GUzAW

Thanks to Ekster Wallets for sponsoring today's video. Head over to https://shop.ekster.com/CraftComputing, or use Promo Code: Craft, and get 35% Off your next order!

How do you make your own AI Generated Images? And how do you train Stable Diffusion to use your face? Today, I'm going to show you how to install and run your own AI Image Generation Server, and teach it who you are.

But first... What am I drinking???

From Barsidious Brewing, it's the BLACK Stout Ale. For an 8% stout, this hits WAY above it class in body and flavor. Highly recommended.

Link to written documentation: https://drive.google.com/drive..../folders/1ZogTG0pMUA

Grab yourself a Pint Glass or Hoodie at https://craftcomputing.store

Follow me on Mastodon @Craftcomputing@hostux.social

Support me on Patreon and get access to my exclusive Discord server. Chat with myself and the other hosts on Talking Heads all week long.

https://www.patreon.com/CraftComputing

Music:
No Good Layabout by Kevin MacLeod
Link: https://incompetech.filmmusic.....io/song/4140-no-good
License: https://filmmusic.io/standard-license

Setup Instructions (Python 3.10.11, 4090, working on Windows): https://pastebin.com/YpqNSHFy

If you are still running into cuda issues after trying p13.txt take a read at this: https://pastebin.com/eSiVGGzA

Requirements:

Probably can run it if you have at least 6Gb of VRAM

Anaconda

Git

Generative-Models github

SVD or SVD_XT

Download Links:

Anaconda: https://www.anaconda.com/download

Git: https://git-scm.com/downloads

Generative-Models Github: https://github.com/Stability-AI/generative-models

SVD: https://huggingface.co/stabili....tyai/stable-video-di

SVD_XT: https://huggingface.co/stabili....tyai/stable-video-di

Info:

Convert your images to videos with Stable Video Diffusion!

https://stability.ai/news/stab....le-video-diffusion-o

This Stable Diffusion inpainting trick will give you great images like never before! Thank you to SpyBG for this awesome trick!

Did you made it work? Let me know in the comments!
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
SOCIAL MEDIA LINKS!
✨ Support my work on Patreon: https://www.patreon.com/aitrepreneur
⚔️ Join the Discord server: https://discord.gg/3ErYSdyUPt
🧠 My Second Channel THE MAKER LAIR: https://bit.ly/themakerlair
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Runpod: https://bit.ly/runpodAi

SpyBG's channel: https://www.youtube.com/@spybgtoolkit

#stablediffusion #shorts #stablediffusiontutorial
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
WATCH MY MOST POPULAR VIDEOS:
RECOMMENDED WATCHING - My "Stable Diffusion" Playlist:
►► https://bit.ly/stablediffusion

RECOMMENDED WATCHING - My "Tutorial" Playlist:
►► https://bit.ly/TuTPlaylist

Disclosure: Bear in mind that some of the links in this post are affiliate links and if you go through them to make a purchase I will earn a commission. Keep in mind that I link these companies and their products because of their quality and not because of the commission I receive from your purchases. The decision is yours, and whether or not you decide to buy something is completely up to you.