Bubble View

NO this is not a pr0n or NSFW model. It is entirely trained on midjourney data that is a mixture of glass/plastic ornament and bubble view of objects and landscapes.

Model used to train: Cheese Daddy's Landscape Mix.

We stream a lot of our testing on twitch: https://www.twitch.tv/duskfallcrew

any chance you can spare a coffee or three? https://ko-fi.com/DUSKFALLcrew

FAQ:

1. What Prompted you to make this? - I like making stupidly quirky things and seeing if shit sticks.

2. How did you train it? WITH MY AUTISTIC INTELLIGENCE (shh it's just the colab notebook)

3. VAE? It's a LORA, use what you want - we reccomend the Waifu ones or anything that gives you vibrant colors, but it's up to you. It's a LORA, and I don't know how that works. We trained it with the same one Kenshi and other mixes use (The Hakurei's waifu one)

4. Why didn't you include a YAML OR VAE? - it's a L O R A. Go download your own favorite toys and mix it with this one. Idgaf, i don't know i Hate math!

5. Model used to train? https://civitai.com/models/5041/cheese-daddys-landscapes-mix So thank you to https://civitai.com/user/cheesedaddy - Cause this mix is amaaaazing.

WHAT is the prompt you used to generate it?

I've been studying the anime geeks:

Pos Prompt: masterpiece, highres, absurdres, best quality, ultra-detailed, illustration, Christmas bulb ornament reflecting a mystical treehouse with intricate golden filigree webbing, tilt shift perspective,((ultra detailed, brush strokes, digital painting, extreme small details inking, glossy surface lighting, saturated lines, inner glow, outer glow, two-toned saturated highlights)), hyper realistic, intense, vivid background, 4k wallpaper, aesthetic, masterpiece, award-winning photography, macro photography vivid colors, photorealistic, atmospheric, cinematic, moody, rule of thirds, majestic, detailed, sharp details, sharp focus

Negative: lowres, bad anatomy, bad hands, nude, nsfw, erotic, naked, nipples, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry

Seed is always -1 cause i'm wild, and I feel like you should always trust the variables. (I have ADHD, i'm lazy leave me alone)