End of training

README.md

@@ -0,0 +1,49 @@
+
+---
+license: creativeml-openrail-m
+base_model: amused/amused-512
+datasets:
+- lambdalabs/pokemon-blip-captions
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+- text-to-image
+- diffusers
+- amused
+inference: true
+---
+    
+# aMUSEd finetuning - suvadityamuk/amused-512-pokemon
+
+This pipeline was finetuned from **amused/amused-512** on the **lambdalabs/pokemon-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['a pokemon red mammoth with unicorn horns', 'a pokemon blue fish with golden scales', 'a pokemon green goblin with glasses, wearing black pants and red shirt', 'a pokemon golden unicorn with shiny black hair and deep blue horns', 'a pokemon drawing of a dragon with its mouth closed', 'a pokemon red and yellow phoenix with fire on its wings', 'a pokemon purple tree with white leaves and golden nectar flowing', 'a pokemon green caterpillar']: 
+
+![val_imgs_grid](./val_imgs_grid.png)
+
+
+## Pipeline usage
+
+You can use the pipeline like so:
+
+```python
+from diffusers import DiffusionPipeline
+import torch
+
+pipeline = DiffusionPipeline.from_pretrained("suvadityamuk/amused-512-pokemon", torch_dtype=torch.float16)
+prompt = "a pokemon red mammoth with unicorn horns"
+image = pipeline(prompt).images[0]
+image.save("my_image.png")
+```
+
+## Training info
+
+These are the key hyperparameters used during training:
+
+* Training Steps: 750
+* Learning rate: 0.00025
+* Batch size: 8
+* Gradient accumulation steps: 4
+* Image resolution: 512
+* Mixed-precision: bf16
+
+
+More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/ml-colabs/fconn-amused/runs/3ob7g307).

checkpoint-100/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1683eb29cdcd208cbe113527361ec1b7e9c50d750808addc6ba356ee90df03a2
+size 1220139006

checkpoint-100/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06103e5fd0312fed5944f9da3b5051257bd838abba5101538151adf1d06bd94
+size 14408

checkpoint-100/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:820d227375038f02873567923da684b2500a67bbf69535a5b7d5b614defc8040
+size 1064

checkpoint-100/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

checkpoint-100/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5b7af94f2fe8e0b4dc96bfc5ad33a729d8736cb350baf29c7cfed96bf0e25ce
+size 2433086672

checkpoint-150/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329ba8511104e68d2f26b8ae3f13613db4ced760197cc1748878c8b8b8fc378a
+size 1220139006

checkpoint-150/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac233f3033045bc63f3dc335435a3214c99827141b65d98fe61dba30c718f2b
+size 14408

checkpoint-150/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a9b838c9e2095eb6039dfd382e4c582c9f02c44adba0f25bcd035aa5af308ce
+size 1064

checkpoint-150/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

checkpoint-150/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c83d2ff81b9e72c1b517e4a54144c7c6dcfa0eda36634895868f28d3fe51d6
+size 2433086672

checkpoint-200/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08eeadfc61dc1e795de818909fe02f159a9302bfed51c73d84b981f4424e5ab
+size 1220139006

checkpoint-200/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4925195ba5c9987fd13d4f63724af4db65aa1a14c4794b4df98600386e6bd0c4
+size 14408

checkpoint-200/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a2c2d65c81d2f1a44c97f02ce25b3c742ec1ac58296e9ead6efbd6f748d93f
+size 1064

checkpoint-200/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

checkpoint-200/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3ff164377bee9e94e9c61a6abb65689852eb26d8e591bd8fd74d1509c94309
+size 2433086672

checkpoint-250/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c75c3e11dac5edc0d2eba01fd26569c30b05bb4029a7d8170ab7d1eb53f846
+size 1220139006

checkpoint-250/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f520d1c2111850f7fa1047511eb1b48e03c2e8c0abce1b5e98eac0a19338c73
+size 14408

checkpoint-250/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67dda8766b47ea0e127a1336bbc2be7ece8f564d45df7238b7e3d8194361dd4f
+size 1064

checkpoint-250/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

checkpoint-250/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8aaeb4fed3ddf5c0a8f2a97256e5ab05f6769975d031198cde7b4b9904f05dc
+size 2433086672

checkpoint-300/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3470436a8b17aa72489369aefd2e410bacde866a163f52c2af88f08662a4c70e
+size 1220139518

checkpoint-300/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e346147a03ca24ecdd1bb847efae9786683f457fb768ca8f003b2f5be5a39ec2
+size 14408

checkpoint-300/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c4f24febed8904edd77d7c3dfeceec80ce8ac46f187c13cc543808d5fa2a7b
+size 1064

checkpoint-300/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

checkpoint-300/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a74a79d68e9d4f7ad28adae7df287770337f384e2bd08877ca36271796d148b
+size 2433086672

checkpoint-350/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2e4b275fe6bba82c43785c2ba715ece61fb98043ae20a2bcffa642d8bb8621
+size 1220139518

checkpoint-350/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94978b2646fdec06f890ebaa4104225beaa69cc95b2da2c27e26c7398d3e0f5b
+size 14408

checkpoint-350/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7905c938ada4fdf1eaae22276888ab17def5f2ad5c8c7e27feb7e9f766c815a
+size 1064

checkpoint-350/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

checkpoint-350/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1642ea86d59f6169fa20e0a35363de93d93d6ef153ceba92abf2478d979ab312
+size 2433086672

checkpoint-400/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05db2dd3635967df6e29f12021cc7ccafe1ede27a68664eff21dd5015574dd65
+size 1220139518

checkpoint-400/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bfa67d701e35cfd335b5c0e28c20a30ce2df5fdd4c44adcfd149a1f2cfabed
+size 14408

checkpoint-400/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b222f50cf4019bf2a4af9801ee61ced983584829f5aab356a024b6284fbfaea
+size 1064

checkpoint-400/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

checkpoint-400/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0935736718730a45ddc37000f8b42b6ce69faf1a6af5c9e90726be8f63d261b0
+size 2433086672

checkpoint-450/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e45db78fa65b9be2a0672aa605a3875991c130f178640281afdeb142954f18
+size 1220139518

checkpoint-450/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4f8b01a2b7867ac246981cb05dd35788dfb8d3339fbb548766d7ca10792c8e
+size 14408

checkpoint-450/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e91f8c4f58670caca9809c6a1d6c46a96f09c4aa89bc32285057132c38d90c
+size 1064

checkpoint-450/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

checkpoint-450/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21fcfe44ac2b68bb69507b683693b5586368c8b77cdf897855fdf6feb9d7f9fc
+size 2433086672

checkpoint-50/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7734a2ea7a0321aa6421cd6826ecd8d4408bdaedce0e03317168c63db38ecf82
+size 1220139006

checkpoint-50/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667e97cf17d191644c0ae93a3c495521d5dac94813457ce8fcd8799ad12da662
+size 14408

checkpoint-50/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3883a4de5fb624ad6d5f7302f4ca52b2725bae30dbb53ff8c7b8829a6b607e
+size 1064

checkpoint-50/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}

checkpoint-50/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553eadeab0752b63c7bdfbee12e95d4d78e0fb6d506df04d3e1bc05880a3ca6f
+size 2433086672

checkpoint-500/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576a413d61622dd1c650853840d62a99d0bf429b01390237113289a627342951
+size 1220139518

checkpoint-500/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8689e4846f44b93c72d286d7345e8cf78f212b50fd0ccfa06293d80fae9186
+size 14408

checkpoint-500/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a64b03d0773f91f522e81c4f703747e71530a9ddde23207251d238f2ace6db2
+size 1064

checkpoint-500/transformer/config.json

@@ -0,0 +1,27 @@
+{
+  "_class_name": "UVit2DModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "_name_or_path": "amused/amused-512",
+  "attention_dropout": 0.0,
+  "block_num_heads": 12,
+  "block_out_channels": 768,
+  "codebook_size": 8192,
+  "cond_embed_dim": 768,
+  "downsample": true,
+  "encoder_hidden_size": 768,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "in_channels": 768,
+  "intermediate_size": 2816,
+  "layer_norm_eps": 1e-06,
+  "ln_elementwise_affine": true,
+  "micro_cond_embed_dim": 1280,
+  "micro_cond_encode_dim": 256,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_res_blocks": 3,
+  "sample_size": 32,
+  "upsample": true,
+  "use_bias": false,
+  "vocab_size": 8256
+}