Text-to-Image
Diffusers
Safetensors
PixArtSigmaPipeline
stable-diffusion
stable-diffusion-diffusers
full
pixart
pixart sigma
Instructions to use TensorFamily/SigmaJourney with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use TensorFamily/SigmaJourney with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TensorFamily/SigmaJourney", dtype=torch.bfloat16, device_map="cuda") prompt = "A blonde sexy girl, wearing glasses at latex shirt and a blue beanie with a tattoo, blue and white, highly detailed, sublime, extremely beautiful, sharp focus, refined, cinematic, intricate, elegant, dynamic, rich deep colors, bright color, shining light, attractive, cute, pretty, background full, epic composition, dramatic atmosphere, radiant, professional, stunning" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Trained for 5 epochs and 6500 steps.
Browse filesTrained with datasets ['text-embeds', 'mj-v6']
Learning rate 8e-06, batch size 32, and 4 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: PixArt-alpha/PixArt-Sigma-XL-2-1024-MS
VAE: madebyollin/sdxl-vae-fp16-fix
- README.md +1 -1
- optimizer.bin +1 -1
- random_states_0.pkl +1 -1
- scheduler.bin +1 -1
- training_state-mj-v6.json +2 -2
- training_state.json +1 -1
- transformer/diffusion_pytorch_model.safetensors +1 -1
README.md
CHANGED
|
@@ -211,7 +211,7 @@ You may reuse the base model text encoder for inference.
|
|
| 211 |
## Training settings
|
| 212 |
|
| 213 |
- Training epochs: 5
|
| 214 |
-
- Training steps:
|
| 215 |
- Learning rate: 8e-06
|
| 216 |
- Effective batch size: 128
|
| 217 |
- Micro-batch size: 32
|
|
|
|
| 211 |
## Training settings
|
| 212 |
|
| 213 |
- Training epochs: 5
|
| 214 |
+
- Training steps: 6500
|
| 215 |
- Learning rate: 8e-06
|
| 216 |
- Effective batch size: 128
|
| 217 |
- Micro-batch size: 32
|
optimizer.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3665677155
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44afaab9255d34407ccdda24cd8d439c1dc2c8b894626b73513c3f99f6884bca
|
| 3 |
size 3665677155
|
random_states_0.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39e5379e888f59465cd27ed54de0dc30d2c13614d6c9fa9d9612180e9def4cc0
|
| 3 |
size 14344
|
scheduler.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82b9181e0fb07684d448c29b119a12ece73f17e76cf041d9866d1abc21f0654b
|
| 3 |
size 1000
|
training_state-mj-v6.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b27a20757ed8b206880c6c3b348d4aa502fbd6fc490aa67d90f0197f93a7a87
|
| 3 |
+
size 20793443
|
training_state.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"global_step":
|
|
|
|
| 1 |
+
{"global_step": 6500, "epoch_step": 1009, "epoch": 6, "exhausted_backends": [], "repeats": {"mj-v6": 0}}
|
transformer/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1221780352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa1de754981329845441044235df9d94a826cf2ee7a3f5b77f1de1c99c35014b
|
| 3 |
size 1221780352
|