|
--- |
|
license: openrail |
|
--- |
|
--- |
|
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](https://civitai.com/models/2385/socalguitarists-magic-facelift-negative-embedding-for-model-2x-fix-yo-ugly-faces) 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. |
|
|
|
<div align="center"> |
|
<img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/00000.png"> |
|
</div> |
|
|
|
<div align="center"> |
|
<img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/00001.png"> |
|
</div> |
|
|
|
<div align="center"> |
|
<img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/00002.png"> |
|
</div> |
|
|
|
<div align="center"> |
|
<img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/00003.png"> |
|
</div> |
|
|
|
--- |
|
**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. |
|
|
|
<div align="center"> |
|
<img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/people_sample.png"> |
|
</div> |
|
|
|
|
|
**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) |
|
|
|
<div align="center"> |
|
<img src="https://huggingface.co/fzbuzz/TungstenDispo-embedding-sd-v2-1/resolve/main/background_sample.png"> |
|
</div> |
|
|
|
|
|
|
|
|
|
|
|
|
