Merge branch 'patrickvonplaten-add_safety_checker' into main

scripts/txt2img.py

@@ -16,12 +16,31 @@ from ldm.util import instantiate_from_config
 from ldm.models.diffusion.ddim import DDIMSampler
 from ldm.models.diffusion.plms import PLMSSampler
 
+from diffusers.pipelines.stable_diffusion.safety_checker import StableDiffusionSafetyChecker
+from transformers import AutoFeatureExtractor
+
+# load safety model
+safety_model_id = "CompVis/stable-diffusion-safety-checker"
+safety_feature_extractor = AutoFeatureExtractor.from_pretrained(safety_model_id)
+safety_checker = StableDiffusionSafetyChecker.from_pretrained(safety_model_id)
 
 def chunk(it, size):
     it = iter(it)
     return iter(lambda: tuple(islice(it, size)), ())
 
 
+def numpy_to_pil(images):
+    """
+    Convert a numpy image or a batch of images to a PIL image.
+    """
+    if images.ndim == 3:
+        images = images[None, ...]
+    images = (images * 255).round().astype("uint8")
+    pil_images = [Image.fromarray(image) for image in images]
+
+    return pil_images
+
+
 def load_model_from_config(config, ckpt, verbose=False):
     print(f"Loading model from {ckpt}")
     pl_sd = torch.load(ckpt, map_location="cpu")
@@ -247,16 +266,23 @@ def main():
 
                         x_samples_ddim = model.decode_first_stage(samples_ddim)
                         x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
+                        x_samples_ddim = x_samples_ddim.cpu().permute(0, 2, 3, 1).numpy()
+
+                        x_image = x_samples_ddim
+                        safety_checker_input = safety_feature_extractor(numpy_to_pil(x_image), return_tensors="pt")
+                        x_checked_image, has_nsfw_concept = safety_checker(images=x_image, clip_input=safety_checker_input.pixel_values)
+
+                        x_checked_image_torch = torch.from_numpy(x_checked_image).permute(0, 3, 1, 2)
 
                         if not opt.skip_save:
-                            for x_sample in x_samples_ddim:
+                            for x_sample in x_checked_image_torch:
                                 x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
                                 Image.fromarray(x_sample.astype(np.uint8)).save(
                                     os.path.join(sample_path, f"{base_count:05}.png"))
                                 base_count += 1
 
                         if not opt.skip_grid:
-                            all_samples.append(x_samples_ddim)
+                            all_samples.append(x_checked_image_torch)
 
                 if not opt.skip_grid:
                     # additionally, save as grid