Edit model card

license: openrail

The embedding were trained using A1111 TI for the 768px Stable Diffusion v2.0 model. The embedding should work on any model that uses SD v2.0 as a base.

TungstenDispo (v1)

The TungstenDispo embedding were trained for 1000 epochs with a gradient batch size of 50. A total of ~100 training images of tungsten photographs taken with CineStill 800T were used. The split was around 50/50 people landscapes.

The effect isn't quite the tungsten photo effect I was going for, but creates very nice, artistic portraits of people. For some of the people, I used SoCalGuitarist's Negative FaceLift as a negative embedding. I used it on 0.3 strength, and it seems like it makes the eyes slightly less wonky. Unclear extent of effect.

Landscapes haven't been experimented with much and are WIP.


Workflow for Above Pictures

Sampler: Euler-A, 20 Steps, CFG: 7.0. Slightly cherry-picked for best pictures. 900x768 -> 4x LDSR upscaled

Negative Prompt for all images (Not entirely sure if all of them matter, but does help a bit):

(Neg_Facelift768:0.3), (blur:0.3), (cropped:1.3), (ugly:1.3), (bad anatomy:1.2), (disfigured:1.1), (deformed:1.1), (bad proportions:1.3), (extra limbs:1.2), (missing fingers:1.2), (extra fingers:1.2), (out of frame:1.3), (makeup:1.1)

Positive Prompts:

First Image:

TungstenDispo, photoshoot of a asian female model with white hair, in a dark room, (closeup:0.2)

Second Image:

(TungstenDispo:1.3), photoshoot of a (model:0.7), posed, in a dark room, highly detailed, (closeup:0.2), (skin pores:0.5)

Third Image:

(TungstenDispo:1.2), photoshoot of a model, posed, in a dark room, (closeup:0.2)

Fourth Image:

TungstenDispo, photoshoot of a male model, posed, in a dark room, (closeup:0.2)

Usage for A1111 WebUI

Download the TungstenDispo.pt file and put in embeddings/. Prepend "TungstenDispo" at start of prompt.

More People Samples w/out exact workflow

Pretty much the same, only changed up subject a little + weights.

Landscape Demo:

Honestly did not turn out as good as anticipated. It really loves neon signs. Stay tuned for more exploration on landscapes :p

Sampler: DDIM, 80 Steps, CFG: 7.0. Slightly cherry-picked for best pictures. 768x1024 Positive Prompt (bolded part altered for image)

(TungstenStyle:1.5), cinematic shot of a (empty:1.5) symmetric glass foyer at night with light faintly shining through the windows, highly detailed

Negative Prompt:

billboards, signs, words, (blur:0.2)

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .