thu-ml
/

unidiffuser-v1

Text-to-Image Diffusers UniDiffuserPipeline image-to-text image-captioning image-variation text-variation multi-modality generative model

Model card Files Files and versions Community

Update README.md

#4

by dg845 - opened May 24, 2023

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -56,7 +56,7 @@ from diffusers import UniDiffuserPipeline
 device = "cuda"
 model_id_or_path = "thu-ml/unidiffuser-v1"
-pipe = UniDiffuserPipeline.from_pretrained(model_id_or_path)
 pipe.to(device)
 # Joint image-text generation. The generation task is automatically inferred.
@@ -89,7 +89,7 @@ init_image = init_image.resize((512, 512))
 sample = pipe(image=init_image, num_inference_steps=20, guidance_scale=8.0)
 i2t_text = sample.text[0]
-print(text)
 # Image variation can be performed with a image-to-text generation followed by a text-to-image generation:
 sample = pipe(prompt=i2t_text, num_inference_steps=20, guidance_scale=8.0)

 device = "cuda"
 model_id_or_path = "thu-ml/unidiffuser-v1"
+pipe = UniDiffuserPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float16)
 pipe.to(device)
 # Joint image-text generation. The generation task is automatically inferred.
 sample = pipe(image=init_image, num_inference_steps=20, guidance_scale=8.0)
 i2t_text = sample.text[0]
+print(i2t_text)
 # Image variation can be performed with a image-to-text generation followed by a text-to-image generation:
 sample = pipe(prompt=i2t_text, num_inference_steps=20, guidance_scale=8.0)