Downloads · 30 days
9
4% of all-time downloads
doodad-v1-2
doohickey/doodad-v1-2
doodad-v1-2 is a text-to-image model from doohickey. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as bigscience-bloom-rail-1.0.
<p style="color:green" <b This is the 1st part of a 2 (3?) part project meant to be used with <a href="https://huggingface.co/doohickey"Doohickey</a </b </p
All-time downloads
241
Public
Repo size
2.7 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin2.7 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- bigscience-bloom-rail-1.0
- Access
- Public
- Created
- Sep 28, 2022
- Updated
- May 5, 2023
- SHA
- c49f2b6a
Model card
From the Hugging Face model README
Doodad
<p style="color:green"> <b> This is 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 style was trained with Dreambooth-Stable and is used with "<doodad>". Tt 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:
- Task
- Text-to-Image
- Library
- diffusers
- License
- bigscience-bloom-rail-1.0
- Languages
- en
- Created
- Sep 28, 2022
- Updated
- May 5, 2023