Stable Diffusion 模型之 Midjourney 开源版 - Openjourney
Openjourney 是由 PromptHero 开发的基于 Midjourney 图像的开源稳定扩散微调模型。
先看看官方的对比效果
左边是 Stable Diffusion v1.5 的结果,右边是 Openjourney 的结果。
Openjourney 使用方法
下载
Openjourney 模型下载连接 下载文件 mdjrny-v4.safetensors 或者 mdjrny-v4.ckpt 到 stable-diffusion-webui/models/Stable-diffusion 目录下,选择模型之后在prompt中加上mdjrny-v4 style
即可。
Openjourney prompt 参考
1
2
3
4
5
Prompt:
mdjrny-v4 style portrait photograph of Madison Beer as Pocahontas, young beautiful native american woman, perfect symmetrical face, indigenes feather jewelry, traditional handmade dress, armed female hunter warrior, (((wild west))) environment, Utah landscape, ultra realistic, concept art, elegant, ((intricate)), ((highly detailed)), depth of field, ((professionally color graded)), soft ambient lighting, dusk, 8k, art by artgerm and greg rutkowski and alphonse mucha
Negative prompt:
(((backlight))), (((dark face))), white fur, (gold fabric), (gold dress), ((cropped head)), ((out of frame)), ((long neck)), deformed, cripple, ugly, additional arms, additional legs, additional head, two heads, multiple people, group of people
1
2
3
4
5
Prompt:
full body cyborg| full-length portrait| detailed face| symmetric| steampunk| cyberpunk| cyborg| intricate detailed| to scale| hyperrealistic| cinematic lighting| digital art| concept art| mdjrny-v4 style
Negative prompt:
bad anatomy| blurry| fuzzy| disfigured| misshaped| mutant| deformed| bad art| out of frame
更多 openjourney prompt 参考在这 https://prompthero.com/openjourney-prompts
Openjourney-v2 使用方法
下载
Openjourney-v2 模型下载连接 它是在 Stable Diffusion 1.5 上进行训练的,使用了60000多张图像,4500 step 和 3 个 epoch,有了很大改进,所以 Openjourney-v2 模型不再需要添加 prompt openjourney-v2 style
。 使用方法:下载文件 openjourney-v2.ckpt 到 stable-diffusion-webui/models/Stable-diffusion 目录下即可使用。