# Stable Diffusion fine-tuning

Isocities
Openrail
An isometric perspective city scene generation model trained based on Stable Diffusion 1.5
Image Generation English
I
Astroboy
48
58
Flux Controlnet Canny
Other
ControlNet Canny model trained for Black Forest Labs' FLUX.1-dev model, used for text-to-image tasks
Text-to-Image English
F
XLabs-AI
5,519
285
Loras
This repository contains all LoRA models released for Stable Diffusion 1.5 and Pony Diffusion v6 XL, providing various artistic style transformation capabilities.
Image Generation
L
pettankoutei
18
13
Test
LoRA model based on Stable Diffusion v1.5 for text-to-image generation
Image Generation
T
shinonome4649ne
494
4
Fantassified Icons V2
Other
Upgraded fantasy-style icon generation model, fine-tuned on Stable Diffusion, optimized for generating game-style item icons
Image Generation Supports Multiple Languages
F
proximasanfinetuning
371
53
Dreambooth Diffusion Minercraft
Openrail
This is a diffusion model fine-tuned based on Minecraft concepts, specializing in generating Minecraft-style landscape images.
Image Generation
D
keras-dreambooth
20
4
Sd Anireal V2.8
Gpl-3.0
An image generation model fine-tuned based on Stable Diffusion 1.5, supporting text-to-image and image-to-image tasks, particularly excelling in realistic style and artistic creation.
Image Generation Supports Multiple Languages
S
circulus
65
2
Gambit And Rogue
Openrail
This is a text-to-image generation model based on Stable Diffusion, specifically designed for creating comic-style illustrations of X-Men characters Gambit and Rogue.
Image Generation English
G
EnD-Diffusers
16
0
Openjourney V2
Openrail
Openjourney v2 is an open-source Stable Diffusion fine-tuned model developed by PromptHero based on 60,000+ Midjourney images, eliminating the need to add 'mdjrny-v4 style' prompts.
Image Generation
O
PeggyWang
15
10
Faucet V1 5
Openrail
faucet-v1.5 is a text-to-image generation model based on Stable Diffusion technology, trained by albburtsev using TheLastBen's fast-DreamBooth notebook.
Image Generation
F
albburtsev
17
1
Sd Photoreal V2.5
Gpl-3.0
High-quality photorealistic image generation model fine-tuned from Stable Diffusion 1.5
Image Generation Supports Multiple Languages
S
circulus
248
5
Aigencloud
Openrail
This is an open-source model based on Stable Diffusion, specifically fine-tuned for Midjourney image styles, capable of generating images with Midjourney characteristics.
Image Generation English
A
dpredrag
25
3
Angele9500
Openrail
A Stable Diffusion model trained based on TheLastBen's fast-DreamBooth notebook, specializing in text-to-image generation tasks.
Image Generation
A
tytfyhutrf
16
0
Sd Photoreal Photo V2
Gpl-3.0
An image generation model fine-tuned based on Stable Diffusion 1.5, specializing in hyper-realistic style photos.
Image Generation Supports Multiple Languages
S
circulus
294
7
Sd Photoreal Semi V2
Gpl-3.0
An image generation model fine-tuned based on Stable Diffusion 1.5, focusing on generating high-quality, realistic images.
Image Generation Supports Multiple Languages
S
circulus
173
4
Sd Anireal 3d V2
Gpl-3.0
A text-to-image model fine-tuned from Stable Diffusion 1.5, specializing in generating 3D-style and realistic art images
Image Generation Supports Multiple Languages
S
circulus
84
10
Sd Anireal 2d V2
Gpl-3.0
An image generation model fine-tuned based on Stable Diffusion 1.5, specializing in generating 2D-style art images
Image Generation Supports Multiple Languages
S
circulus
85
5
Bpmodel
Openrail
The BP Model is an experimental Stable Diffusion model based on Joseph Cheung's ACertainty, focusing on high-resolution (768/1024) anime-style image generation.
Image Generation English
B
Crosstyan
1,296
152
Riffusion
Openrail
A real-time music generation model based on Stable Diffusion technology that generates spectrograms from text input and converts them into audio clips
Text-to-Audio
R
Narsil
14
1
Openjourney V4
Openrail
A text-to-image model trained on 124,000 Midjourney v4 images using the Stable Diffusion v1.5 framework
Image Generation
O
prompthero
62.14k
1,243
Redshift Diffusion 768
A high-quality 3D style text-to-image model fine-tuned from Stable Diffusion 2.0, with 768x768 resolution. Use 'redshift style' in prompts to trigger the effect
Image Generation English
R
nitrosocke
36
141
Deathnote
Openrail
A Stable Diffusion model fine-tuned on images from the anime 'Death Note', capable of generating specific characters and items.
Image Generation English
D
Guizmus
146
19
Waifu Diffusers
An anime-style text-to-image model fine-tuned on Stable Diffusion 2.1, trained with 110,000 Danbooru dataset images
Image Generation English
W
Nilaier
96
43
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase