Hugging Face's logo

tuwonga
/
supermarionation

Text-to-Image Diffusers StableDiffusionPipeline stable-diffusion Inference Endpoints
Model card Files Community
3
tuwonga commited on
Commit
96dad62
•
1 Parent(s): de58135

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -9
README.md CHANGED
@@ -11,23 +11,29 @@ This is a fine-tuned Stable Diffusion model (based on v1.5) trained on screensho
11
  _Download the ckpt file from "files and versions" tab into the stable diffusion models folder of your web-ui of choice._
12
  _I've found interesting (and really funny ^^) the output in the img2img. You can see the results in the second and third pic (original/img2img). You can play around with denoising strength (40-70) and activate or not the restore face option._
13
 
 
 
14
 
15
- -- **Characters rendered with this model:**
16
- ![Character Samples](https://huggingface.co/tuwonga/supermarionation/resolve/main/supermarionation_prev1.jpg)
17
- _prompt and settings used: **[person] in supermarionation style** | **Steps: 40, Sampler: Euler, CFG scale: 7.5**_
18
 
19
 
20
  **Characters rendered with img2img:**
21
- ![Character Samples](https://huggingface.co/tuwonga/supermarionation/resolve/main/supermarionation_prev2.jpg)
22
- _prompt and settings used: **[person] in supermarionation style** | **Steps: 40 - you can play around with settings**_
23
 
24
 
25
- **Characters rendered with img2img:**
26
- ![Character Samples](https://huggingface.co/tuwonga/supermarionation/resolve/main/supermarionation_prev3.jpg)
27
- _prompt and settings used: **[person] in supermarionation style** | **Steps: 40 - you can play around with settings**_
 
 
 
 
28
 
29
  --
30
- This model was trained with Dreambooth training by TheLastBen, using 43 images at 8600 steps with 18% of text encoder.
31
  --
32
  ## License
33
  This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
11
  _Download the ckpt file from "files and versions" tab into the stable diffusion models folder of your web-ui of choice._
12
  _I've found interesting (and really funny ^^) the output in the img2img. You can see the results in the second and third pic (original/img2img). You can play around with denoising strength (40-70) and activate or not the restore face option._
13
 
14
+ ### supermarionation v2
15
+ In this version I've trained characters and vehicles. 47 images and 9400 steps, 20% text encoder.
16
 
17
+ -- **Characters and vehicles rendered with this model:**
18
+ ![Character Samples](https://huggingface.co/tuwonga/supermarionation/resolve/main/supermarionation_v2_prev1.jpg)
19
+ _prompt and settings used: **[person/vehicle] in supermarionation style** | **Steps: 30, Sampler: Euler, CFG scale: 7.5**_
20
 
21
 
22
  **Characters rendered with img2img:**
23
+ ![Character Samples](https://huggingface.co/tuwonga/supermarionation/resolve/main/supermarionation_v2_prev2.jpg)
24
+ _prompt and settings used: **[person] in supermarionation style** | **Steps: 30 - you can play around with settings**_
25
 
26
 
27
+ **Characters rendered with supermarionation in txt2img:**
28
+ ![Character Samples](https://huggingface.co/tuwonga/supermarionation/resolve/main/supermarionation_prev1.jpg)
29
+ _prompt and settings used: **[person] in supermarionation style** | **Steps: 40 - you can play around with settings**_
30
+
31
+ **Characters rendered with supermarionation in img2img:**
32
+ ![Character Samples](https://huggingface.co/tuwonga/supermarionation/resolve/main/supermarionation_prev2.jpg)
33
+ _prompt and settings used: **[person] in supermarionation style** | **Steps: 40 - you can play around with settings**_
34
 
35
  --
36
+ Supermarionation v1 was trained with Dreambooth training by TheLastBen, using 43 images at 8600 steps with 18% of text encoder.
37
  --
38
  ## License
39
  This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.