I Tested 161 Stable Diffusion 1.5 Models: Best for Realism, Anime and 3D + 1-Click Download (2024)
Kohya GUI configs for SD 1.5 based models DreamBooth / full fine-tuning, the very best of over 70 trainings, in three tiers from 10.2 GB to 22 GB VRAM.
Published Jan 23, 2024 · 5,807 views · Watch on YouTube
Get the app and files

Kohya GUI SD 1.5 DreamBooth / Full Fine-Tuning Workflow & Config
Kohya GUI configs for SD 1.5 based models DreamBooth / full fine-tuning, the very best of over 70 trainings, in three tiers from 10.2 GB to 22 GB VRAM.

OneTrainer SD 1.5 DreamBooth / Fine Tuning Best Configs & Workflow
OneTrainer configs for SD 1.5 based models DreamBooth / full fine tuning, from over 70 trainings; 8 presets from 7 GB to 48 GB VRAM with measured speeds.

Stable Diffusion 1.5 Models: 1-Click Download of the 160 Best
Stable Diffusion 1.5 model downloader that fetches the 160 very best SD 1.5 based models from CivitAI and Hugging Face in one click, 409 GB in total.
Chapters
- 0:00 Introduction to the very best Stable Diffusion 1.5 custom models hosted on CivitAI
- 3:36 How to 1 click download all of the 161+ SD 1.5 based models on to your computer
- 3:48 How to change the default download location for the models
- 4:13 How to start download progress of all SD 1.5 models
- 4:49 What to do if errors occurs during the download
- 5:18 How all of the downloaded models looks like in the folder
- 5:32 The disk space requirement of all of the models
- 5:42 How to disable download of the unwanted models
- 5:54 How to download models on RunPod - follow same strategy for all other platforms
- 8:27 How to download over 1 gigapixel X/Y/Z comparison images for all SD 1.5 models
- 9:16 Why I did test photo of man, picture of a man and image of a man prompts
- 9:35 How to open X/Y/Z grid files
- 9:45 Starting to analyze photo of a man X/Y/Z grid for 161 SD 1.5 very best models
- 19:19 Overfit vs generalized model comparison
- 32:03 What difference photo vs image vs picture prompt makes
- 32:25 Image of a man prompt results
- 33:33 Comparison of 1024x1024 pixel resolution capability of Stable Diffusion 1.5 based models
- 34:05 What happens when you generate images in a higher resolution
- 35:13 The models that can handle 1024x1024 pixel resolution output
- 45:45 What I am going to do as a next step
About this video
In this video, I am excited to present a comprehensive tutorial featuring a script for downloading over 160 of the finest Stable Diffusion 1.5 (SD 1.5) models. In addition, I have meticulously tested and compared each of these 161 top-tier CivitAI SD 1.5 models, providing detailed commentary on their performance and capabilities.
Models Downloader Script And The Patreon Post Shown In The Video ⤵️
https://www.patreon.com/posts/1-click-download-96666744
Stable Diffusion GitHub repository ⤵️
https://github.com/FurkanGozukara/Stable-Diffusion
SECourses Discord To Get Full Support ⤵️
https://discord.com/servers/software-engineering-courses-secourses-772774097734074388
The tested and compared models full list:
3D_Cartoon_Vision
AbsoluteReality_8_1
AbyssOrangeMix2
AingDiffusion5
Airtist_MAL_Realistic_5
AmIReal_3
amour_bold_5
AnalogMadness_v_7
AniMerge_6
AniMics
AniToon_1
AniVerse_6
AnRealSpiceMix
AnReal
AnyLoRA
AnyLoRA_Anime_Mix_v1
Arthemy_Comics_v_6
Arthemy_Real
Art_Universe_v_8
AWPortrait_2
A_Zovya_Photoreal
BeautyFool_UltraReal
Beauty_By_Stable_Yogi
BeenYou_R13
Beyond_Reality
Blazing_Drive_v13_md
blue_pencil0
Cheese_Daddy_Landscapes_1
ChikMix
Colorful_v_8
Consistent_Factor_Euclid_v6_1
Corbe_Realism_Mix