Text-to-Image
Diffusers
Safetensors
English
StableDiffusionPipeline
anime
art
general
MichaelFan
stable-diffusion
stable-diffusion-diffusers
Instructions to use Yntec/OpenLexica with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Yntec/OpenLexica with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Yntec/OpenLexica", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update unet/config.json
Browse files- unet/config.json +1 -4
unet/config.json
CHANGED
|
@@ -1,12 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "UNet2DConditionModel",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"act_fn": "silu",
|
| 5 |
"addition_embed_type": null,
|
| 6 |
"addition_embed_type_num_heads": 64,
|
| 7 |
"addition_time_embed_dim": null,
|
| 8 |
"attention_head_dim": 8,
|
| 9 |
-
"attention_type": "default",
|
| 10 |
"block_out_channels": [
|
| 11 |
320,
|
| 12 |
640,
|
|
@@ -27,7 +26,6 @@
|
|
| 27 |
"DownBlock2D"
|
| 28 |
],
|
| 29 |
"downsample_padding": 1,
|
| 30 |
-
"dropout": 0.0,
|
| 31 |
"dual_cross_attention": false,
|
| 32 |
"encoder_hid_dim": null,
|
| 33 |
"encoder_hid_dim_type": null,
|
|
@@ -48,7 +46,6 @@
|
|
| 48 |
"resnet_out_scale_factor": 1.0,
|
| 49 |
"resnet_skip_time_act": false,
|
| 50 |
"resnet_time_scale_shift": "default",
|
| 51 |
-
"reverse_transformer_layers_per_block": null,
|
| 52 |
"sample_size": 96,
|
| 53 |
"time_cond_proj_dim": null,
|
| 54 |
"time_embedding_act_fn": null,
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.19.0.dev0",
|
| 4 |
"act_fn": "silu",
|
| 5 |
"addition_embed_type": null,
|
| 6 |
"addition_embed_type_num_heads": 64,
|
| 7 |
"addition_time_embed_dim": null,
|
| 8 |
"attention_head_dim": 8,
|
|
|
|
| 9 |
"block_out_channels": [
|
| 10 |
320,
|
| 11 |
640,
|
|
|
|
| 26 |
"DownBlock2D"
|
| 27 |
],
|
| 28 |
"downsample_padding": 1,
|
|
|
|
| 29 |
"dual_cross_attention": false,
|
| 30 |
"encoder_hid_dim": null,
|
| 31 |
"encoder_hid_dim_type": null,
|
|
|
|
| 46 |
"resnet_out_scale_factor": 1.0,
|
| 47 |
"resnet_skip_time_act": false,
|
| 48 |
"resnet_time_scale_shift": "default",
|
|
|
|
| 49 |
"sample_size": 96,
|
| 50 |
"time_cond_proj_dim": null,
|
| 51 |
"time_embedding_act_fn": null,
|