@jacobwjs reports dynamic thresholding works very well and 0.95 is a better value

.github/FUNDING.yml

@@ -1 +1 @@
-github: [lucidrains]
+github: [nousr, Veldrovive, lucidrains]

README.md

@@ -628,6 +628,82 @@ images = dalle2(
 
 Now you'll just have to worry about training the Prior and the Decoder!
 
+## Inpainting
+
+Inpainting is also built into the `Decoder`. You simply have to pass in the `inpaint_image` and `inpaint_mask` (boolean tensor where `True` indicates which regions of the inpaint image to keep)
+
+This repository uses the formulation put forth by <a href="https://arxiv.org/abs/2201.09865">Lugmayr et al. in Repaint</a>
+
+```python
+import torch
+from dalle2_pytorch import Unet, Decoder, CLIP
+
+# trained clip from step 1
+
+clip = CLIP(
+    dim_text = 512,
+    dim_image = 512,
+    dim_latent = 512,
+    num_text_tokens = 49408,
+    text_enc_depth = 6,
+    text_seq_len = 256,
+    text_heads = 8,
+    visual_enc_depth = 6,
+    visual_image_size = 256,
+    visual_patch_size = 32,
+    visual_heads = 8
+).cuda()
+
+# 2 unets for the decoder (a la cascading DDPM)
+
+unet = Unet(
+    dim = 16,
+    image_embed_dim = 512,
+    cond_dim = 128,
+    channels = 3,
+    dim_mults = (1, 1, 1, 1)
+).cuda()
+
+
+# decoder, which contains the unet(s) and clip
+
+decoder = Decoder(
+    clip = clip,
+    unet = (unet,),               # insert both unets in order of low resolution to highest resolution (you can have as many stages as you want here)
+    image_sizes = (256,),         # resolutions, 256 for first unet, 512 for second. these must be unique and in ascending order (matches with the unets passed in)
+    timesteps = 1000,
+    image_cond_drop_prob = 0.1,
+    text_cond_drop_prob = 0.5
+).cuda()
+
+# mock images (get a lot of this)
+
+images = torch.randn(4, 3, 256, 256).cuda()
+
+# feed images into decoder, specifying which unet you want to train
+# each unet can be trained separately, which is one of the benefits of the cascading DDPM scheme
+
+loss = decoder(images, unet_number = 1)
+loss.backward()
+
+# do the above for many steps for both unets
+
+mock_image_embed = torch.randn(1, 512).cuda()
+
+# then to do inpainting
+
+inpaint_image = torch.randn(1, 3, 256, 256).cuda()      # (batch, channels, height, width)
+inpaint_mask = torch.ones(1, 256, 256).bool().cuda()    # (batch, height, width)
+
+inpainted_images = decoder.sample(
+    image_embed = mock_image_embed,
+    inpaint_image = inpaint_image,    # just pass in the inpaint image
+    inpaint_mask = inpaint_mask       # and the mask
+)
+
+inpainted_images.shape # (1, 3, 256, 256)
+```
+
 ## Experimental
 
 ### DALL-E2 with Latent Diffusion
@@ -991,26 +1067,12 @@ dataset = ImageEmbeddingDataset(
 )
 ```
 
-### Scripts (wip)
+### Scripts
 
 #### `train_diffusion_prior.py`
 
 For detailed information on training the diffusion prior, please refer to the [dedicated readme](prior.md)
 
-## CLI (wip)
-
-```bash
-$ dream 'sharing a sunset at the summit of mount everest with my dog'
-```
-
-Once built, images will be saved to the same directory the command is invoked
-
-<a href="https://github.com/lucidrains/big-sleep">template</a>
-
-## Training CLI (wip)
-
-<a href="https://github.com/lucidrains/stylegan2-pytorch">template</a>
-
 ## Todo
 
 - [x] finish off gaussian diffusion class for latent embedding - allow for prediction of epsilon
@@ -1048,11 +1110,10 @@ Once built, images will be saved to the same directory the command is invoked
 - [x] bring in skip-layer excitations (from lightweight gan paper) to see if it helps for either decoder of unet or vqgan-vae training (doesnt work well)
 - [x] test out grid attention in cascading ddpm locally, decide whether to keep or remove https://arxiv.org/abs/2204.01697 (keeping, seems to be fine)
 - [x] allow for unet to be able to condition non-cross attention style as well
-- [ ] become an expert with unets, cleanup unet code, make it fully configurable, port all learnings over to https://github.com/lucidrains/x-unet (test out unet² in ddpm repo) - consider https://github.com/lucidrains/uformer-pytorch attention-based unet
-- [ ] speed up inference, read up on papers (ddim or diffusion-gan, etc)
-- [ ] figure out if possible to augment with external memory, as described in https://arxiv.org/abs/2204.11824
+- [x] speed up inference, read up on papers (ddim)
+- [x] add inpainting ability using resampler from repaint paper https://arxiv.org/abs/2201.09865
+- [ ] try out the nested unet from https://arxiv.org/abs/2005.09007 after hearing several positive testimonies from researchers, for segmentation anyhow
 - [ ] interface out the vqgan-vae so a pretrained one can be pulled off the shelf to validate latent diffusion + DALL-E2
-- [ ] add inpainting ability using resampler from repaint paper https://arxiv.org/abs/2201.09865
 
 ## Citations
 
@@ -1170,4 +1231,14 @@ Once built, images will be saved to the same directory the command is invoked
 }
 ```
 
+```bibtex
+@article{Lugmayr2022RePaintIU,
+    title   = {RePaint: Inpainting using Denoising Diffusion Probabilistic Models},
+    author  = {Andreas Lugmayr and Martin Danelljan and Andr{\'e}s Romero and Fisher Yu and Radu Timofte and Luc Van Gool},
+    journal = {ArXiv},
+    year    = {2022},
+    volume  = {abs/2201.09865}
+}
+```
+
 *Creating noise from data is easy; creating data from noise is generative modeling.* - <a href="https://arxiv.org/abs/2011.13456">Yang Song's paper</a>

dalle2_pytorch/dalle2_pytorch.py

@@ -52,10 +52,10 @@ def first(arr, d = None):
 
 def maybe(fn):
     @wraps(fn)
-    def inner(x):
+    def inner(x, *args, **kwargs):
         if not exists(x):
             return x
-        return fn(x)
+        return fn(x, *args, **kwargs)
     return inner
 
 def default(val, d):
@@ -63,13 +63,13 @@ def default(val, d):
         return val
     return d() if callable(d) else d
 
-def cast_tuple(val, length = None):
+def cast_tuple(val, length = None, validate = True):
     if isinstance(val, list):
         val = tuple(val)
 
     out = val if isinstance(val, tuple) else ((val,) * default(length, 1))
 
-    if exists(length):
+    if exists(length) and validate:
         assert len(out) == length
 
     return out
@@ -146,7 +146,7 @@ def resize_image_to(
         scale_factors = target_image_size / orig_image_size
         out = resize(image, scale_factors = scale_factors, **kwargs)
     else:
-        out = F.interpolate(image, target_image_size, mode = 'nearest', align_corners = False)
+        out = F.interpolate(image, target_image_size, mode = 'nearest')
 
     if exists(clamp_range):
         out = out.clamp(*clamp_range)
@@ -278,6 +278,7 @@ class OpenAIClipAdapter(BaseClipAdapter):
         import clip
         openai_clip, preprocess = clip.load(name)
         super().__init__(openai_clip)
+        self.eos_id = 49407 # for handling 0 being also '!'
 
         text_attention_final = self.find_layer('ln_final')
         self.handle = text_attention_final.register_forward_hook(self._hook)
@@ -316,7 +317,10 @@ class OpenAIClipAdapter(BaseClipAdapter):
     @torch.no_grad()
     def embed_text(self, text):
         text = text[..., :self.max_text_len]
-        text_mask = text != 0
+
+        is_eos_id = (text == self.eos_id)
+        text_mask_excluding_eos = is_eos_id.cumsum(dim = -1) == 0
+        text_mask = F.pad(text_mask_excluding_eos, (1, -1), value = True)
         assert not self.cleared
 
         text_embed = self.clip.encode_text(text)
@@ -490,6 +494,9 @@ class NoiseScheduler(nn.Module):
         self.has_p2_loss_reweighting = p2_loss_weight_gamma > 0.
         register_buffer('p2_loss_weight', (p2_loss_weight_k + alphas_cumprod / (1 - alphas_cumprod)) ** -p2_loss_weight_gamma)
 
+    def sample_random_times(self, batch):
+        return torch.randint(0, self.num_timesteps, (batch,), device = self.betas.device, dtype = torch.long)
+
     def q_posterior(self, x_start, x_t, t):
         posterior_mean = (
             extract(self.posterior_mean_coef1, t, x_t.shape) * x_start +
@@ -515,7 +522,7 @@ class NoiseScheduler(nn.Module):
 
     def predict_noise_from_start(self, x_t, t, x0):
         return (
-            (x0 - extract(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t) / \
+            (extract(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t - x0) / \
             extract(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)
         )
 
@@ -900,7 +907,7 @@ class DiffusionPriorNetwork(nn.Module):
         null_text_embeds = self.null_text_embed.to(text_encodings.dtype)
 
         text_encodings = torch.where(
-            rearrange(mask, 'b n -> b n 1'),
+            rearrange(mask, 'b n -> b n 1').clone(),
             text_encodings,
             null_text_embeds
         )
@@ -1239,7 +1246,7 @@ class DiffusionPrior(nn.Module):
         # timestep conditioning from ddpm
 
         batch, device = image_embed.shape[0], image_embed.device
-        times = torch.randint(0, self.noise_scheduler.num_timesteps, (batch,), device = device, dtype = torch.long)
+        times = self.noise_scheduler.sample_random_times(batch)
 
         # scale image embed (Katherine)
 
@@ -1535,9 +1542,10 @@ class Unet(nn.Module):
         self_attn = False,
         attn_dim_head = 32,
         attn_heads = 16,
-        lowres_cond = False, # for cascading diffusion - https://cascaded-diffusion.github.io/
+        lowres_cond = False,             # for cascading diffusion - https://cascaded-diffusion.github.io/
+        lowres_noise_cond = False,       # for conditioning on low resolution noising, based on Imagen
         sparse_attn = False,
-        attend_at_middle = True, # whether to have a layer of attention at the bottleneck (can turn off for higher resolution in cascading DDPM, before bringing in efficient attention)
+        attend_at_middle = True,         # whether to have a layer of attention at the bottleneck (can turn off for higher resolution in cascading DDPM, before bringing in efficient attention)
         cond_on_text_encodings = False,
         max_text_len = 256,
         cond_on_image_embeds = False,
@@ -1546,6 +1554,7 @@ class Unet(nn.Module):
         init_conv_kernel_size = 7,
         resnet_groups = 8,
         num_resnet_blocks = 2,
+        init_cross_embed = True,
         init_cross_embed_kernel_sizes = (3, 7, 15),
         cross_embed_downsample = False,
         cross_embed_downsample_kernel_sizes = (2, 4),
@@ -1574,7 +1583,7 @@ class Unet(nn.Module):
         init_channels = channels if not lowres_cond else channels * 2 # in cascading diffusion, one concats the low resolution image, blurred, for conditioning the higher resolution synthesis
         init_dim = default(init_dim, dim)
 
-        self.init_conv = CrossEmbedLayer(init_channels, dim_out = init_dim, kernel_sizes = init_cross_embed_kernel_sizes, stride = 1)
+        self.init_conv = CrossEmbedLayer(init_channels, dim_out = init_dim, kernel_sizes = init_cross_embed_kernel_sizes, stride = 1) if init_cross_embed else nn.Conv2d(init_channels, init_dim, init_conv_kernel_size, padding = init_conv_kernel_size // 2)
 
         dims = [init_dim, *map(lambda m: dim * m, dim_mults)]
         in_out = list(zip(dims[:-1], dims[1:]))
@@ -1624,6 +1633,17 @@ class Unet(nn.Module):
             self.text_to_cond = nn.Linear(text_embed_dim, cond_dim)
             self.text_embed_dim = text_embed_dim
 
+        # low resolution noise conditiong, based on Imagen's upsampler training technique
+
+        self.lowres_noise_cond = lowres_noise_cond
+
+        self.to_lowres_noise_cond = nn.Sequential(
+            SinusoidalPosEmb(dim),
+            nn.Linear(dim, time_cond_dim),
+            nn.GELU(),
+            nn.Linear(time_cond_dim, time_cond_dim)
+        ) if lowres_noise_cond else None
+
         # finer control over whether to condition on image embeddings and text encodings
         # so one can have the latter unets in the cascading DDPMs only focus on super-resoluting
 
@@ -1727,7 +1747,10 @@ class Unet(nn.Module):
             ]))
 
         self.final_resnet_block = ResnetBlock(dim * 2, dim, time_cond_dim = time_cond_dim, groups = top_level_resnet_group)
-        self.to_out = nn.Conv2d(dim, self.channels_out, kernel_size = final_conv_kernel_size, padding = final_conv_kernel_size // 2)
+
+        out_dim_in = dim + (channels if lowres_cond else 0)
+
+        self.to_out = nn.Conv2d(out_dim_in, self.channels_out, kernel_size = final_conv_kernel_size, padding = final_conv_kernel_size // 2)
 
         zero_init_(self.to_out) # since both OpenAI and @crowsonkb are doing it
 
@@ -1737,15 +1760,17 @@ class Unet(nn.Module):
         self,
         *,
         lowres_cond,
+        lowres_noise_cond,
         channels,
         channels_out,
         cond_on_image_embeds,
-        cond_on_text_encodings
+        cond_on_text_encodings,
     ):
         if lowres_cond == self.lowres_cond and \
             channels == self.channels and \
             cond_on_image_embeds == self.cond_on_image_embeds and \
             cond_on_text_encodings == self.cond_on_text_encodings and \
+            cond_on_lowres_noise == self.cond_on_lowres_noise and \
             channels_out == self.channels_out:
             return self
 
@@ -1754,7 +1779,8 @@ class Unet(nn.Module):
             channels = channels,
             channels_out = channels_out,
             cond_on_image_embeds = cond_on_image_embeds,
-            cond_on_text_encodings = cond_on_text_encodings
+            cond_on_text_encodings = cond_on_text_encodings,
+            lowres_noise_cond = lowres_noise_cond
         )
 
         return self.__class__(**{**self._locals, **updated_kwargs})
@@ -1780,6 +1806,7 @@ class Unet(nn.Module):
         *,
         image_embed,
         lowres_cond_img = None,
+        lowres_noise_level = None,
         text_encodings = None,
         image_cond_drop_prob = 0.,
         text_cond_drop_prob = 0.,
@@ -1808,6 +1835,13 @@ class Unet(nn.Module):
         time_tokens = self.to_time_tokens(time_hiddens)
         t = self.to_time_cond(time_hiddens)
 
+        # low res noise conditioning (similar to time above)
+
+        if exists(lowres_noise_level):
+            assert exists(self.to_lowres_noise_cond), 'lowres_noise_cond must be set to True on instantiation of the unet in order to conditiong on lowres noise'
+            lowres_noise_level = lowres_noise_level.type_as(x)
+            t = t + self.to_lowres_noise_cond(lowres_noise_level)
+
         # conditional dropout
 
         image_keep_mask = prob_mask_like((batch_size,), 1 - image_cond_drop_prob, device = device)
@@ -1919,7 +1953,7 @@ class Unet(nn.Module):
                 hiddens.append(x)
 
             x = attn(x)
-            hiddens.append(x)
+            hiddens.append(x.contiguous())
 
             if exists(post_downsample):
                 x = post_downsample(x)
@@ -1947,44 +1981,68 @@ class Unet(nn.Module):
         x = torch.cat((x, r), dim = 1)
 
         x = self.final_resnet_block(x, t)
+
+        if exists(lowres_cond_img):
+            x = torch.cat((x, lowres_cond_img), dim = 1)
+
         return self.to_out(x)
 
 class LowresConditioner(nn.Module):
     def __init__(
         self,
         downsample_first = True,
-        downsample_mode_nearest = False,
+        use_blur = True,
         blur_prob = 0.5,
         blur_sigma = 0.6,
         blur_kernel_size = 3,
-        input_image_range = None
+        use_noise = False,
+        input_image_range = None,
+        normalize_img_fn = identity,
+        unnormalize_img_fn = identity
     ):
         super().__init__()
         self.downsample_first = downsample_first
-        self.downsample_mode_nearest = downsample_mode_nearest
-
         self.input_image_range = input_image_range
 
+        self.use_blur = use_blur
         self.blur_prob = blur_prob
         self.blur_sigma = blur_sigma
         self.blur_kernel_size = blur_kernel_size
 
+        self.use_noise = use_noise
+        self.normalize_img = normalize_img_fn
+        self.unnormalize_img = unnormalize_img_fn
+        self.noise_scheduler = NoiseScheduler(beta_schedule = 'linear', timesteps = 1000, loss_type = 'l2') if use_noise else None
+
+    def noise_image(self, cond_fmap, noise_levels = None):
+        assert exists(self.noise_scheduler)
+
+        batch = cond_fmap.shape[0]
+        cond_fmap = self.normalize_img(cond_fmap)
+
+        random_noise_levels = default(noise_levels, lambda: self.noise_scheduler.sample_random_times(batch))
+        cond_fmap = self.noise_scheduler.q_sample(cond_fmap, t = random_noise_levels, noise = torch.randn_like(cond_fmap))
+
+        cond_fmap = self.unnormalize_img(cond_fmap)
+        return cond_fmap, random_noise_levels
+
     def forward(
         self,
         cond_fmap,
         *,
         target_image_size,
         downsample_image_size = None,
+        should_blur = True,
         blur_sigma = None,
         blur_kernel_size = None
     ):
         if self.downsample_first and exists(downsample_image_size):
-            cond_fmap = resize_image_to(cond_fmap, downsample_image_size, clamp_range = self.input_image_range, nearest = self.downsample_mode_nearest)
+            cond_fmap = resize_image_to(cond_fmap, downsample_image_size, clamp_range = self.input_image_range, nearest = True)
 
         # blur is only applied 50% of the time
         # section 3.1 in https://arxiv.org/abs/2106.15282
 
-        if random.random() < self.blur_prob:
+        if self.use_blur and should_blur and random.random() < self.blur_prob:
 
             # when training, blur the low resolution conditional image
 
@@ -2006,8 +2064,21 @@ class LowresConditioner(nn.Module):
 
             cond_fmap = gaussian_blur2d(cond_fmap, cast_tuple(blur_kernel_size, 2), cast_tuple(blur_sigma, 2))
 
-        cond_fmap = resize_image_to(cond_fmap, target_image_size, clamp_range = self.input_image_range)
-        return cond_fmap
+        # resize to target image size
+
+        cond_fmap = resize_image_to(cond_fmap, target_image_size, clamp_range = self.input_image_range, nearest = True)
+
+        # noise conditioning, as done in Imagen
+        # as a replacement for the BSR noising, and potentially replace blurring for first stage too
+
+        random_noise_levels = None
+
+        if self.use_noise:
+            cond_fmap, random_noise_levels = self.noise_image(cond_fmap)
+
+        # return conditioning feature map, as well as the augmentation noise levels
+
+        return cond_fmap, random_noise_levels
 
 class Decoder(nn.Module):
     def __init__(
@@ -2028,11 +2099,13 @@ class Decoder(nn.Module):
         predict_x_start_for_latent_diffusion = False,
         image_sizes = None,                         # for cascading ddpm, image size at each stage
         random_crop_sizes = None,                   # whether to random crop the image at that stage in the cascade (super resoluting convolutions at the end may be able to generalize on smaller crops)
+        use_noise_for_lowres_cond = False,          # whether to use Imagen-like noising for low resolution conditioning  
+        use_blur_for_lowres_cond = True,            # whether to use the blur conditioning used in the original cascading ddpm paper, as well as DALL-E2
         lowres_downsample_first = True,             # cascading ddpm - resizes to lower resolution, then to next conditional resolution + blur
-        lowres_downsample_mode_nearest = False,     # cascading ddpm - whether to use nearest mode downsampling for lower resolution
         blur_prob = 0.5,                            # cascading ddpm - when training, the gaussian blur is only applied 50% of the time
         blur_sigma = 0.6,                           # cascading ddpm - blur sigma
         blur_kernel_size = 3,                       # cascading ddpm - blur kernel size
+        lowres_noise_sample_level = 0.2,            # in imagen paper, they use a 0.2 noise level at sample time for low resolution conditioning
         clip_denoised = True,
         clip_x_start = True,
         clip_adapter_overrides = dict(),
@@ -2042,7 +2115,7 @@ class Decoder(nn.Module):
         unconditional = False,                      # set to True for generating images without conditioning
         auto_normalize_img = True,                  # whether to take care of normalizing the image from [0, 1] to [-1, 1] and back automatically - you can turn this off if you want to pass in the [-1, 1] ranged image yourself from the dataloader
         use_dynamic_thres = False,                  # from the Imagen paper
-        dynamic_thres_percentile = 0.9,
+        dynamic_thres_percentile = 0.95,
         p2_loss_weight_gamma = 0.,                  # p2 loss weight, from https://arxiv.org/abs/2204.00227 - 0 is equivalent to weight of 1 across time - 1. is recommended
         p2_loss_weight_k = 1,
         ddim_sampling_eta = 1.                      # can be set to 0. for deterministic sampling afaict
@@ -2080,10 +2153,17 @@ class Decoder(nn.Module):
 
         self.channels = channels
 
+
+        # normalize and unnormalize image functions
+
+        self.normalize_img = normalize_neg_one_to_one if auto_normalize_img else identity
+        self.unnormalize_img = unnormalize_zero_to_one if auto_normalize_img else identity
+
         # verify conditioning method
 
         unets = cast_tuple(unet)
         num_unets = len(unets)
+        self.num_unets = num_unets
 
         self.unconditional = unconditional
 
@@ -2099,12 +2179,28 @@ class Decoder(nn.Module):
         self.learned_variance_constrain_frac = learned_variance_constrain_frac # whether to constrain the output of the network (the interpolation fraction) from 0 to 1
         self.vb_loss_weight = vb_loss_weight
 
+        # default and validate conditioning parameters
+
+        use_noise_for_lowres_cond = cast_tuple(use_noise_for_lowres_cond, num_unets - 1, validate = False)
+        use_blur_for_lowres_cond = cast_tuple(use_blur_for_lowres_cond, num_unets - 1, validate = False)
+
+        if len(use_noise_for_lowres_cond) < num_unets:
+            use_noise_for_lowres_cond = (False, *use_noise_for_lowres_cond)
+
+        if len(use_blur_for_lowres_cond) < num_unets:
+            use_blur_for_lowres_cond = (False, *use_blur_for_lowres_cond)
+
+        assert not use_noise_for_lowres_cond[0], 'first unet will never need low res noise conditioning'
+        assert not use_blur_for_lowres_cond[0], 'first unet will never need low res blur conditioning'
+
+        assert num_unets == 1 or all((use_noise or use_blur) for use_noise, use_blur in zip(use_noise_for_lowres_cond[1:], use_blur_for_lowres_cond[1:]))
+
         # construct unets and vaes
 
         self.unets = nn.ModuleList([])
         self.vaes = nn.ModuleList([])
 
-        for ind, (one_unet, one_vae, one_unet_learned_var) in enumerate(zip(unets, vaes, learned_variance)):
+        for ind, (one_unet, one_vae, one_unet_learned_var, lowres_noise_cond) in enumerate(zip(unets, vaes, learned_variance, use_noise_for_lowres_cond)):
             assert isinstance(one_unet, Unet)
             assert isinstance(one_vae, (VQGanVAE, NullVQGanVAE))
 
@@ -2116,6 +2212,7 @@ class Decoder(nn.Module):
 
             one_unet = one_unet.cast_model_parameters(
                 lowres_cond = not is_first,
+                lowres_noise_cond = lowres_noise_cond,
                 cond_on_image_embeds = not unconditional and is_first,
                 cond_on_text_encodings = not unconditional and one_unet.cond_on_text_encodings,
                 channels = unet_channels,
@@ -2158,13 +2255,14 @@ class Decoder(nn.Module):
         image_sizes = default(image_sizes, (image_size,))
         image_sizes = tuple(sorted(set(image_sizes)))
 
-        assert len(self.unets) == len(image_sizes), f'you did not supply the correct number of u-nets ({len(self.unets)}) for resolutions {image_sizes}'
+        assert self.num_unets == len(image_sizes), f'you did not supply the correct number of u-nets ({self.num_unets}) for resolutions {image_sizes}'
         self.image_sizes = image_sizes
         self.sample_channels = cast_tuple(self.channels, len(image_sizes))
 
         # random crop sizes (for super-resoluting unets at the end of cascade?)
 
         self.random_crop_sizes = cast_tuple(random_crop_sizes, len(image_sizes))
+        assert not exists(self.random_crop_sizes[0]), 'you would not need to randomly crop the image for the base unet'
 
         # predict x0 config
 
@@ -2177,18 +2275,30 @@ class Decoder(nn.Module):
         # cascading ddpm related stuff
 
         lowres_conditions = tuple(map(lambda t: t.lowres_cond, self.unets))
-        assert lowres_conditions == (False, *((True,) * (len(self.unets) - 1))), 'the first unet must be unconditioned (by low resolution image), and the rest of the unets must have `lowres_cond` set to True'
+        assert lowres_conditions == (False, *((True,) * (num_unets - 1))), 'the first unet must be unconditioned (by low resolution image), and the rest of the unets must have `lowres_cond` set to True'
 
-        self.lowres_downsample_mode_nearest = lowres_downsample_mode_nearest
+        self.lowres_conds = nn.ModuleList([])
 
-        self.to_lowres_cond = LowresConditioner(
-            downsample_first = lowres_downsample_first,
-            downsample_mode_nearest = lowres_downsample_mode_nearest,
-            blur_prob = blur_prob,
-            blur_sigma = blur_sigma,
-            blur_kernel_size = blur_kernel_size,
-            input_image_range = self.input_image_range
-        )
+        for unet_index, use_noise, use_blur in zip(range(num_unets), use_noise_for_lowres_cond, use_blur_for_lowres_cond):
+            if unet_index == 0:
+                self.lowres_conds.append(None)
+                continue
+
+            lowres_cond = LowresConditioner(
+                downsample_first = lowres_downsample_first,
+                use_blur = use_blur,
+                use_noise = use_noise,
+                blur_prob = blur_prob,
+                blur_sigma = blur_sigma,
+                blur_kernel_size = blur_kernel_size,
+                input_image_range = self.input_image_range,
+                normalize_img_fn = self.normalize_img,
+                unnormalize_img_fn = self.unnormalize_img
+            )
+
+            self.lowres_conds.append(lowres_cond)
+
+        self.lowres_noise_sample_level = lowres_noise_sample_level
 
         # classifier free guidance
 
@@ -2206,11 +2316,6 @@ class Decoder(nn.Module):
         self.use_dynamic_thres = use_dynamic_thres
         self.dynamic_thres_percentile = dynamic_thres_percentile
 
-        # normalize and unnormalize image functions
-
-        self.normalize_img = normalize_neg_one_to_one if auto_normalize_img else identity
-        self.unnormalize_img = unnormalize_zero_to_one if auto_normalize_img else identity
-
         # device tracker
 
         self.register_buffer('_dummy', torch.Tensor([True]), persistent = False)
@@ -2224,7 +2329,7 @@ class Decoder(nn.Module):
         return any([unet.cond_on_text_encodings for unet in self.unets])
 
     def get_unet(self, unet_number):
-        assert 0 < unet_number <= len(self.unets)
+        assert 0 < unet_number <= self.num_unets
         index = unet_number - 1
         return self.unets[index]
 
@@ -2266,10 +2371,10 @@ class Decoder(nn.Module):
         x = x.clamp(-s, s) / s
         return x
 
-    def p_mean_variance(self, unet, x, t, image_embed, noise_scheduler, text_encodings = None, lowres_cond_img = None, clip_denoised = True, predict_x_start = False, learned_variance = False, cond_scale = 1., model_output = None):
+    def p_mean_variance(self, unet, x, t, image_embed, noise_scheduler, text_encodings = None, lowres_cond_img = None, clip_denoised = True, predict_x_start = False, learned_variance = False, cond_scale = 1., model_output = None, lowres_noise_level = None):
         assert not (cond_scale != 1. and not self.can_classifier_guidance), 'the decoder was not trained with conditional dropout, and thus one cannot use classifier free guidance (cond_scale anything other than 1)'
 
-        pred = default(model_output, lambda: unet.forward_with_cond_scale(x, t, image_embed = image_embed, text_encodings = text_encodings, cond_scale = cond_scale, lowres_cond_img = lowres_cond_img))
+        pred = default(model_output, lambda: unet.forward_with_cond_scale(x, t, image_embed = image_embed, text_encodings = text_encodings, cond_scale = cond_scale, lowres_cond_img = lowres_cond_img, lowres_noise_level = lowres_noise_level))
 
         if learned_variance:
             pred, var_interp_frac_unnormalized = pred.chunk(2, dim = 1)
@@ -2301,44 +2406,97 @@ class Decoder(nn.Module):
         return model_mean, posterior_variance, posterior_log_variance
 
     @torch.no_grad()
-    def p_sample(self, unet, x, t, image_embed, noise_scheduler, text_encodings = None, cond_scale = 1., lowres_cond_img = None, predict_x_start = False, learned_variance = False, clip_denoised = True):
+    def p_sample(self, unet, x, t, image_embed, noise_scheduler, text_encodings = None, cond_scale = 1., lowres_cond_img = None, predict_x_start = False, learned_variance = False, clip_denoised = True, lowres_noise_level = None):
         b, *_, device = *x.shape, x.device
-        model_mean, _, model_log_variance = self.p_mean_variance(unet, x = x, t = t, image_embed = image_embed, text_encodings = text_encodings, cond_scale = cond_scale, lowres_cond_img = lowres_cond_img, clip_denoised = clip_denoised, predict_x_start = predict_x_start, noise_scheduler = noise_scheduler, learned_variance = learned_variance)
+        model_mean, _, model_log_variance = self.p_mean_variance(unet, x = x, t = t, image_embed = image_embed, text_encodings = text_encodings, cond_scale = cond_scale, lowres_cond_img = lowres_cond_img, clip_denoised = clip_denoised, predict_x_start = predict_x_start, noise_scheduler = noise_scheduler, learned_variance = learned_variance, lowres_noise_level = lowres_noise_level)
         noise = torch.randn_like(x)
         # no noise when t == 0
         nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
         return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
 
     @torch.no_grad()
-    def p_sample_loop_ddpm(self, unet, shape, image_embed, noise_scheduler, predict_x_start = False, learned_variance = False, clip_denoised = True, lowres_cond_img = None, text_encodings = None, cond_scale = 1, is_latent_diffusion = False):
+    def p_sample_loop_ddpm(
+        self,
+        unet,
+        shape,
+        image_embed,
+        noise_scheduler,
+        predict_x_start = False,
+        learned_variance = False,
+        clip_denoised = True,
+        lowres_cond_img = None,
+        text_encodings = None,
+        cond_scale = 1,
+        is_latent_diffusion = False,
+        lowres_noise_level = None,
+        inpaint_image = None,
+        inpaint_mask = None
+    ):
         device = self.device
 
         b = shape[0]
         img = torch.randn(shape, device = device)
 
+        if exists(inpaint_image):
+            inpaint_image = self.normalize_img(inpaint_image)
+            inpaint_image = resize_image_to(inpaint_image, shape[-1], nearest = True)
+            inpaint_mask = rearrange(inpaint_mask, 'b h w -> b 1 h w').float()
+            inpaint_mask = resize_image_to(inpaint_mask, shape[-1], nearest = True)
+            inpaint_mask = inpaint_mask.bool()
+
         if not is_latent_diffusion:
             lowres_cond_img = maybe(self.normalize_img)(lowres_cond_img)
 
         for i in tqdm(reversed(range(0, noise_scheduler.num_timesteps)), desc = 'sampling loop time step', total = noise_scheduler.num_timesteps):
+            times = torch.full((b,), i, device = device, dtype = torch.long)
+
+            if exists(inpaint_image):
+                # following the repaint paper
+                # https://arxiv.org/abs/2201.09865
+                noised_inpaint_image = noise_scheduler.q_sample(inpaint_image, t = times)
+                img = (img * ~inpaint_mask) + (noised_inpaint_image * inpaint_mask)
+
             img = self.p_sample(
                 unet,
                 img,
-                torch.full((b,), i, device = device, dtype = torch.long),
+                times,
                 image_embed = image_embed,
                 text_encodings = text_encodings,
                 cond_scale = cond_scale,
                 lowres_cond_img = lowres_cond_img,
+                lowres_noise_level = lowres_noise_level,
                 predict_x_start = predict_x_start,
                 noise_scheduler = noise_scheduler,
                 learned_variance = learned_variance,
                 clip_denoised = clip_denoised
             )
 
+        if exists(inpaint_image):
+            img = (img * ~inpaint_mask) + (inpaint_image * inpaint_mask)
+
         unnormalize_img = self.unnormalize_img(img)
         return unnormalize_img
 
     @torch.no_grad()
-    def p_sample_loop_ddim(self, unet, shape, image_embed, noise_scheduler, timesteps, eta = 1., predict_x_start = False, learned_variance = False, clip_denoised = True, lowres_cond_img = None, text_encodings = None, cond_scale = 1, is_latent_diffusion = False):
+    def p_sample_loop_ddim(
+        self,
+        unet,
+        shape,
+        image_embed,
+        noise_scheduler,
+        timesteps,
+        eta = 1.,
+        predict_x_start = False,
+        learned_variance = False,
+        clip_denoised = True,
+        lowres_cond_img = None,
+        text_encodings = None,
+        cond_scale = 1,
+        is_latent_diffusion = False,
+        lowres_noise_level = None,
+        inpaint_image = None,
+        inpaint_mask = None
+    ):
         batch, device, total_timesteps, alphas, eta = shape[0], self.device, noise_scheduler.num_timesteps, noise_scheduler.alphas_cumprod_prev, self.ddim_sampling_eta
 
         times = torch.linspace(0., total_timesteps, steps = timesteps + 2)[:-1]
@@ -2346,6 +2504,13 @@ class Decoder(nn.Module):
         times = list(reversed(times.int().tolist()))
         time_pairs = list(zip(times[:-1], times[1:]))
 
+        if exists(inpaint_image):
+            inpaint_image = self.normalize_img(inpaint_image)
+            inpaint_image = resize_image_to(inpaint_image, shape[-1], nearest = True)
+            inpaint_mask = rearrange(inpaint_mask, 'b h w -> b 1 h w').float()
+            inpaint_mask = resize_image_to(inpaint_mask, shape[-1], nearest = True)
+            inpaint_mask = inpaint_mask.bool()
+
         img = torch.randn(shape, device = device)
 
         if not is_latent_diffusion:
@@ -2357,7 +2522,13 @@ class Decoder(nn.Module):
 
             time_cond = torch.full((batch,), time, device = device, dtype = torch.long)
 
-            pred = unet.forward_with_cond_scale(img, time_cond, image_embed = image_embed, text_encodings = text_encodings, cond_scale = cond_scale, lowres_cond_img = lowres_cond_img)
+            if exists(inpaint_image):
+                # following the repaint paper
+                # https://arxiv.org/abs/2201.09865
+                noised_inpaint_image = noise_scheduler.q_sample(inpaint_image, t = time_cond)
+                img = (img * ~inpaint_mask) + (noised_inpaint_image * inpaint_mask)
+
+            pred = unet.forward_with_cond_scale(img, time_cond, image_embed = image_embed, text_encodings = text_encodings, cond_scale = cond_scale, lowres_cond_img = lowres_cond_img, lowres_noise_level = lowres_noise_level)
 
             if learned_variance:
                 pred, _ = pred.chunk(2, dim = 1)
@@ -2380,6 +2551,9 @@ class Decoder(nn.Module):
                   c1 * noise + \
                   c2 * pred_noise
 
+        if exists(inpaint_image):
+            img = (img * ~inpaint_mask) + (inpaint_image * inpaint_mask)
+
         img = self.unnormalize_img(img)
         return img
 
@@ -2396,7 +2570,7 @@ class Decoder(nn.Module):
 
         return self.p_sample_loop_ddim(*args, noise_scheduler = noise_scheduler, timesteps = timesteps, **kwargs)
 
-    def p_losses(self, unet, x_start, times, *, image_embed, noise_scheduler, lowres_cond_img = None, text_encodings = None, predict_x_start = False, noise = None, learned_variance = False, clip_denoised = False, is_latent_diffusion = False):
+    def p_losses(self, unet, x_start, times, *, image_embed, noise_scheduler, lowres_cond_img = None, text_encodings = None, predict_x_start = False, noise = None, learned_variance = False, clip_denoised = False, is_latent_diffusion = False, lowres_noise_level = None):
         noise = default(noise, lambda: torch.randn_like(x_start))
 
         # normalize to [-1, 1]
@@ -2415,6 +2589,7 @@ class Decoder(nn.Module):
             image_embed = image_embed,
             text_encodings = text_encodings,
             lowres_cond_img = lowres_cond_img,
+            lowres_noise_level = lowres_noise_level,
             image_cond_drop_prob = self.image_cond_drop_prob,
             text_cond_drop_prob = self.text_cond_drop_prob,
         )
@@ -2478,6 +2653,8 @@ class Decoder(nn.Module):
         cond_scale = 1.,
         stop_at_unet_number = None,
         distributed = False,
+        inpaint_image = None,
+        inpaint_mask = None
     ):
         assert self.unconditional or exists(image_embed), 'image embed must be present on sampling from decoder unless if trained unconditionally'
 
@@ -2491,19 +2668,32 @@ class Decoder(nn.Module):
         assert not (self.condition_on_text_encodings and not exists(text_encodings)), 'text or text encodings must be passed into decoder if specified'
         assert not (not self.condition_on_text_encodings and exists(text_encodings)), 'decoder specified not to be conditioned on text, yet it is presented'
 
+        assert not (exists(inpaint_image) ^ exists(inpaint_mask)), 'inpaint_image and inpaint_mask (boolean mask of [batch, height, width]) must be both given for inpainting'
+
         img = None
         is_cuda = next(self.parameters()).is_cuda
 
-        for unet_number, unet, vae, channel, image_size, predict_x_start, learned_variance, noise_scheduler, sample_timesteps in tqdm(zip(range(1, len(self.unets) + 1), self.unets, self.vaes, self.sample_channels, self.image_sizes, self.predict_x_start, self.learned_variance, self.noise_schedulers, self.sample_timesteps)):
+        num_unets = self.num_unets
+        cond_scale = cast_tuple(cond_scale, num_unets)
+
+        for unet_number, unet, vae, channel, image_size, predict_x_start, learned_variance, noise_scheduler, lowres_cond, sample_timesteps, unet_cond_scale in tqdm(zip(range(1, num_unets + 1), self.unets, self.vaes, self.sample_channels, self.image_sizes, self.predict_x_start, self.learned_variance, self.noise_schedulers, self.lowres_conds, self.sample_timesteps, cond_scale)):
 
             context = self.one_unet_in_gpu(unet = unet) if is_cuda and not distributed else null_context()
 
             with context:
-                lowres_cond_img = None
+                # prepare low resolution conditioning for upsamplers
+
+                lowres_cond_img = lowres_noise_level = None
                 shape = (batch_size, channel, image_size, image_size)
 
                 if unet.lowres_cond:
-                    lowres_cond_img = resize_image_to(img, target_image_size = image_size, clamp_range = self.input_image_range, nearest = self.lowres_downsample_mode_nearest)
+                    lowres_cond_img = resize_image_to(img, target_image_size = image_size, clamp_range = self.input_image_range, nearest = True)
+
+                    if lowres_cond.use_noise:
+                        lowres_noise_level = torch.full((batch_size,), int(self.lowres_noise_sample_level * 1000), dtype = torch.long, device = self.device)
+                        lowres_cond_img, _ = lowres_cond.noise_image(lowres_cond_img, lowres_noise_level)
+
+                # latent diffusion
 
                 is_latent_diffusion = isinstance(vae, VQGanVAE)
                 image_size = vae.get_encoded_fmap_size(image_size)
@@ -2511,19 +2701,24 @@ class Decoder(nn.Module):
 
                 lowres_cond_img = maybe(vae.encode)(lowres_cond_img)
 
+                # denoising loop for image
+
                 img = self.p_sample_loop(
                     unet,
                     shape,
                     image_embed = image_embed,
                     text_encodings = text_encodings,
-                    cond_scale = cond_scale,
+                    cond_scale = unet_cond_scale,
                     predict_x_start = predict_x_start,
                     learned_variance = learned_variance,
                     clip_denoised = not is_latent_diffusion,
                     lowres_cond_img = lowres_cond_img,
+                    lowres_noise_level = lowres_noise_level,
                     is_latent_diffusion = is_latent_diffusion,
                     noise_scheduler = noise_scheduler,
-                    timesteps = sample_timesteps
+                    timesteps = sample_timesteps,
+                    inpaint_image = inpaint_image,
+                    inpaint_mask = inpaint_mask
                 )
 
                 img = vae.decode(img)
@@ -2542,7 +2737,7 @@ class Decoder(nn.Module):
         unet_number = None,
         return_lowres_cond_image = False # whether to return the low resolution conditioning images, for debugging upsampler purposes
     ):
-        assert not (len(self.unets) > 1 and not exists(unet_number)), f'you must specify which unet you want trained, from a range of 1 to {len(self.unets)}, if you are training cascading DDPM (multiple unets)'
+        assert not (self.num_unets > 1 and not exists(unet_number)), f'you must specify which unet you want trained, from a range of 1 to {self.num_unets}, if you are training cascading DDPM (multiple unets)'
         unet_number = default(unet_number, 1)
         unet_index = unet_number - 1
 
@@ -2550,6 +2745,7 @@ class Decoder(nn.Module):
 
         vae                 = self.vaes[unet_index]
         noise_scheduler     = self.noise_schedulers[unet_index]
+        lowres_conditioner  = self.lowres_conds[unet_index]
         target_image_size   = self.image_sizes[unet_index]
         predict_x_start     = self.predict_x_start[unet_index]
         random_crop_size    = self.random_crop_sizes[unet_index]
@@ -2572,8 +2768,8 @@ class Decoder(nn.Module):
         assert not (self.condition_on_text_encodings and not exists(text_encodings)), 'text or text encodings must be passed into decoder if specified'
         assert not (not self.condition_on_text_encodings and exists(text_encodings)), 'decoder specified not to be conditioned on text, yet it is presented'
 
-        lowres_cond_img = self.to_lowres_cond(image, target_image_size = target_image_size, downsample_image_size = self.image_sizes[unet_index - 1]) if unet_number > 1 else None
-        image = resize_image_to(image, target_image_size)
+        lowres_cond_img, lowres_noise_level = lowres_conditioner(image, target_image_size = target_image_size, downsample_image_size = self.image_sizes[unet_index - 1]) if exists(lowres_conditioner) else (None, None)
+        image = resize_image_to(image, target_image_size, nearest = True)
 
         if exists(random_crop_size):
             aug = K.RandomCrop((random_crop_size, random_crop_size), p = 1.)
@@ -2590,7 +2786,7 @@ class Decoder(nn.Module):
             image = vae.encode(image)
             lowres_cond_img = maybe(vae.encode)(lowres_cond_img)
 
-        losses = self.p_losses(unet, image, times, image_embed = image_embed, text_encodings = text_encodings, lowres_cond_img = lowres_cond_img, predict_x_start = predict_x_start, learned_variance = learned_variance, is_latent_diffusion = is_latent_diffusion, noise_scheduler = noise_scheduler)
+        losses = self.p_losses(unet, image, times, image_embed = image_embed, text_encodings = text_encodings, lowres_cond_img = lowres_cond_img, predict_x_start = predict_x_start, learned_variance = learned_variance, is_latent_diffusion = is_latent_diffusion, noise_scheduler = noise_scheduler, lowres_noise_level = lowres_noise_level)
 
         if not return_lowres_cond_image:
             return losses

dalle2_pytorch/train_configs.py

@@ -225,6 +225,7 @@ class UnetConfig(BaseModel):
     self_attn: ListOrTuple(int)
     attn_dim_head: int = 32
     attn_heads: int = 16
+    init_cross_embed: bool = True
 
     class Config:
         extra = "allow"

dalle2_pytorch/trainer.py

@@ -673,8 +673,14 @@ class DecoderTrainer(nn.Module):
     def sample(self, *args, **kwargs):
         distributed = self.accelerator.num_processes > 1
         base_decoder = self.accelerator.unwrap_model(self.decoder)
+
+        was_training = base_decoder.training
+        base_decoder.eval()
+
         if kwargs.pop('use_non_ema', False) or not self.use_ema:
-            return base_decoder.sample(*args, **kwargs, distributed = distributed)
+            out = base_decoder.sample(*args, **kwargs, distributed = distributed)
+            base_decoder.train(was_training)
+            return out
 
         trainable_unets = self.accelerator.unwrap_model(self.decoder).unets
         base_decoder.unets = self.unets                  # swap in exponential moving averaged unets for sampling
@@ -687,6 +693,7 @@ class DecoderTrainer(nn.Module):
         for ema in self.ema_unets:
             ema.restore_ema_model_device()
 
+        base_decoder.train(was_training)
         return output
 
     @torch.no_grad()

dalle2_pytorch/version.py

@@ -1 +1 @@
-__version__ = '0.23.6'
+__version__ = '0.26.1'