How to Generate INSANE AI Art for Beginners (Stable Diffusion)
Вставка
- Опубліковано 15 лип 2024
- In this episode, we're exploring the powerful Protogen 2.2 model in Stable Diffusion to create stunning AI art using txt2img. We'll take you through the whole process, showing you how to use Protogen 2.2 to generate unique artwork from text and images. So don't miss out on this exciting episode of creating AI art with Stable Diffusion and Protogen 2.2. Join us now and let's get creative!
💎 Download Sample Images:
cmdelavega.gumroad.com/l/aiart
💎 Chapters
00:00 Intro
00:11 Using Txt2Img
04:60 Generating Anime style
06:16 Upscaling
💎 Protogen 2.2 Model
huggingface.co/darkstorm2150/...
#stablediffusion #aiart #midjourney
Make an animation guide in sd! Different ways, with a green background and different animation styles, thank you in advance! I recently tried to do animation on a green background-and everything seems to be fine-but I can't completely remove the background-in places it remains and it's not very good-especially when the character turns!??
the episode on video to animation comes out this sunday. its the workflow I used for this video: ua-cam.com/users/shorts8MAkC8Wz69k?feature=share I'm using After Effects Keylight to remove the green screen.
@@cmdelavega ok,thanks!
@@cmdelavega I only have the after effects of 2017, I tried different ways to remove the background, but it turns out that the background remains on the character itself and green highlights are visible when moving!?
@A͟l͟e͟k͟s͟a͟n͟d͟r͟ V͟i͟d͟e͟o͟ A͟r͟t͟ D͟e͟s͟i͟g͟n͟ play with clip black and clip white in Keylight. Add the Advanced Spill Suppressor effect and Refine Hard Matte to help with the edges.
@@cmdelavega thanks:)
Sir, I have seen your video thoroughly. When I click "GENERATE" then it shows "RuntimeError: Could not allocate tensor with 33554432 bytes. There is not enough GPU video memory available!" I have 4 GB VRam.
github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Troubleshooting
If you have 4GB VRAM and want to make 512x512 (or maybe up to 640x640)
images, use --medvram
If you have 4GB VRAM and want to make 512x512 images, but you get an out of memory error with --medvram, use --lowvram --always-batch-cond-uncond instead.
If you have 4GB VRAM and want to make images larger than you can with --medvram, use --lowvram.