Downloads · 30 days
4
7% of all-time downloads
2cabda5b-4e53-40e9-8fcf-cdba5ea5bd6c
tzvc/2cabda5b-4e53-40e9-8fcf-cdba5ea5bd6c
2cabda5b-4e53-40e9-8fcf-cdba5ea5bd6c is a text-to-image model from tzvc. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
All-time downloads
60
Public
Repo size
7.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin5.5 GB · 72%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Dec 14, 2022
- Updated
- Dec 14, 2022
- SHA
- da88f934
Try a prompt
Model card
From the Hugging Face model README
training params
{
"pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5",
"instance_data_dir": "./2cabda5b-4e53-40e9-8fcf-cdba5ea5bd6c/instance_data",
"class_data_dir": "./class_data/a-portrait-of-a-person",
"output_dir": "./2cabda5b-4e53-40e9-8fcf-cdba5ea5bd6c/",
"train_text_encoder": true,
"with_prior_preservation": false,
"prior_loss_weight": 1.0,
"instance_prompt": "a portrait of [V]",
"class_prompt": "a portrait of a person",
"resolution": 512,
"train_batch_size": 1,
"gradient_accumulation_steps": 1,
"gradient_checkpointing": true,
"use_8bit_adam": true,
"learning_rate": 5e-06,
"lr_scheduler": "constant",
"lr_warmup_steps": 0,
"num_class_images": 200,
"max_train_steps": 1050,
"mixed_precision": "fp16"
}
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Created
- Dec 14, 2022
- Updated
- Dec 14, 2022