Downloads · 30 days
0
doodad-v1-3-ckpt
doohickey/doodad-v1-3-ckpt
doodad-v1-3-ckpt is a text-to-image model from doohickey. Use it when you need an image from a text prompt. The card lists the license as bigscience-bloom-rail-1.0.
<p style="color:green" <b This is (A converted version of) the 1st part of a 2 (3?) part project meant to be used with <a href="https://huggingface.co/doohickey"Doohickey</a </b </p
Access
Public
Updated Oct 16, 2022
Repo size
2.1 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.ckpt2.1 GB · 100%
At a glance
- Task
- Text-to-Image
- License
- bigscience-bloom-rail-1.0
- Access
- Public
- Created
- Oct 16, 2022
- Updated
- Oct 16, 2022
- SHA
- bd69b580
Model card
From the Hugging Face model README
Doodad.ckpt
<p style="color:green"> <b> This is (A converted version of) the 1st part of a 2 (3?) part project meant to be used with <a href="https://huggingface.co/doohickey">Doohickey</a> </b> </p>
The model was trained with Dreambooth-Stable. It mixes especially well with the <midj-strong> style included in Doohickey. It's a finetuned version of the Trinart-Waifu-diffusion-50-50 included in this organization's models and was trained on 48 images from the author's (crumb's) Pinterest feed.
| Parameter | Value |
|---|---|
| resolution | 512 |
| train_batch_size | 1 |
| gradient_accumulation_steps | 2 |
| learning_rate | 5e-6 |
| num_class_images | 120 |
| max_train_steps | 1200 |
Example outputs:
"portal to another dimension"
"a portrait of a dying god"
"photograph"
- Task
- Text-to-Image
- License
- bigscience-bloom-rail-1.0
- Languages
- en
- Created
- Oct 16, 2022
- Updated
- Oct 16, 2022