Text-to-Image
Diffusers
UniDiffuserPipeline
image-to-text
image-captioning
image-variation
text-variation
multi-modality
generative model
Instructions to use dg845/unidiffuser-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dg845/unidiffuser-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dg845/unidiffuser-diffusers", 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
Upload model_index.json
Browse filesUpdate model_index.json file (rename image_processor to clip_image_processor)
- model_index.json +5 -5
model_index.json
CHANGED
|
@@ -1,6 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "UniDiffuserPipeline",
|
| 3 |
-
"_diffusers_version": "0.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"clip_tokenizer": [
|
| 5 |
"transformers",
|
| 6 |
"CLIPTokenizer"
|
|
@@ -9,10 +13,6 @@
|
|
| 9 |
"transformers",
|
| 10 |
"CLIPVisionModelWithProjection"
|
| 11 |
],
|
| 12 |
-
"image_processor": [
|
| 13 |
-
"transformers",
|
| 14 |
-
"CLIPImageProcessor"
|
| 15 |
-
],
|
| 16 |
"scheduler": [
|
| 17 |
"diffusers",
|
| 18 |
"DPMSolverMultistepScheduler"
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "UniDiffuserPipeline",
|
| 3 |
+
"_diffusers_version": "0.21.0.dev0",
|
| 4 |
+
"clip_image_processor": [
|
| 5 |
+
"transformers",
|
| 6 |
+
"CLIPImageProcessor"
|
| 7 |
+
],
|
| 8 |
"clip_tokenizer": [
|
| 9 |
"transformers",
|
| 10 |
"CLIPTokenizer"
|
|
|
|
| 13 |
"transformers",
|
| 14 |
"CLIPVisionModelWithProjection"
|
| 15 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"scheduler": [
|
| 17 |
"diffusers",
|
| 18 |
"DPMSolverMultistepScheduler"
|