forked from ai-forever/Kandinsky-2
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
65 changed files
with
2,742 additions
and
1,736 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,3 +1,6 @@ | ||
| # Custom | ||
| .DS_Store | ||
|
|
||
| # Byte-compiled / optimized / DLL files | ||
| __pycache__/ | ||
| *.py[cod] | ||
|
|
||
Binary file not shown.
Large diffs are not rendered by default.
Oops, something went wrong.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,163 @@ | ||
| CONFIG_2_0 = { | ||
| "model_config": { | ||
| "image_size": 64, | ||
| "num_channels": 384, | ||
| "num_res_blocks": 3, | ||
| "channel_mult": "", | ||
| "num_heads": 1, | ||
| "num_head_channels": 64, | ||
| "num_heads_upsample": -1, | ||
| "attention_resolutions": "32,16,8", | ||
| "dropout": 0, | ||
| "model_dim": 768, | ||
| "use_scale_shift_norm": True, | ||
| "resblock_updown": True, | ||
| "use_fp16": False, | ||
| "cache_text_emb": True, | ||
| "text_encoder_in_dim1": 1024, | ||
| "text_encoder_in_dim2": 640, | ||
| "pooling_type": "from_model", | ||
| "in_channels": 4, | ||
| "out_channels": 8, | ||
| "up": False, | ||
| "inpainting": False, | ||
| }, | ||
| "diffusion_config": { | ||
| "learn_sigma": True, | ||
| "sigma_small": False, | ||
| "steps": 1000, | ||
| "noise_schedule": "linear", | ||
| "timestep_respacing": "", | ||
| "use_kl": False, | ||
| "predict_xstart": False, | ||
| "rescale_timesteps": True, | ||
| "rescale_learned_sigmas": True, | ||
| "linear_start": 0.0001, | ||
| "linear_end": 0.02, | ||
| }, | ||
| "image_enc_params": { | ||
| "name": "AutoencoderKL", | ||
| "scale": 0.0512, | ||
| "params": { | ||
| "ckpt_path": "", | ||
| "embed_dim": 4, | ||
| "ddconfig": { | ||
| "double_z": True, | ||
| "z_channels": 4, | ||
| "resolution": 256, | ||
| "in_channels": 3, | ||
| "out_ch": 3, | ||
| "ch": 128, | ||
| "ch_mult": [1, 2, 4, 4], | ||
| "num_res_blocks": 2, | ||
| "attn_resolutions": [], | ||
| "dropout": 0.0, | ||
| }, | ||
| }, | ||
| }, | ||
| "text_enc_params1": {"model_path": "", "model_name": "multiclip"}, | ||
| "text_enc_params2": {"model_path": "", "model_name": "MT5EncoderModel"}, | ||
| "tokenizer_name1": "", | ||
| "tokenizer_name2": "", | ||
| } | ||
|
|
||
| CONFIG_2_1 = { | ||
| "clip_name": "ViT-L/14", | ||
| "clip_image_size": 224, | ||
| "tokenizer_name": "", | ||
| "image_enc_params": { | ||
| "name": "MOVQ", | ||
| "scale": 1, | ||
| "ckpt_path": "", | ||
| "params": { | ||
| "embed_dim": 4, | ||
| "n_embed": 16384, | ||
| "ddconfig": { | ||
| "double_z": False, | ||
| "z_channels": 4, | ||
| "resolution": 256, | ||
| "in_channels": 3, | ||
| "out_ch": 3, | ||
| "ch": 128, | ||
| "ch_mult": [1, 2, 2, 4], | ||
| "num_res_blocks": 2, | ||
| "attn_resolutions": [32], | ||
| "dropout": 0.0, | ||
| }, | ||
| }, | ||
| }, | ||
| "text_enc_params": { | ||
| "model_path": "", | ||
| "model_name": "multiclip", | ||
| "in_features": 1024, | ||
| "out_features": 768, | ||
| }, | ||
| "prior": { | ||
| "clip_mean_std_path": "ViT-L-14_stats.th", | ||
| "params": { | ||
| "model": { | ||
| "type": "prior", | ||
| "diffusion_sampler": "uniform", | ||
| "hparams": { | ||
| "text_ctx": 77, | ||
| "xf_width": 2048, | ||
| "xf_layers": 20, | ||
| "xf_heads": 32, | ||
| "xf_final_ln": True, | ||
| "xf_padding": False, | ||
| "text_drop": 0.2, | ||
| "clip_dim": 768, | ||
| "clip_xf_width": 768, | ||
| }, | ||
| }, | ||
| "diffusion": { | ||
| "steps": 1000, | ||
| "learn_sigma": False, | ||
| "sigma_small": True, | ||
| "noise_schedule": "cosine", | ||
| "use_kl": False, | ||
| "predict_xstart": True, | ||
| "rescale_learned_sigmas": False, | ||
| "timestep_respacing": "", | ||
| }, | ||
| }, | ||
| }, | ||
| "model_config": { | ||
| "version": "2.1", | ||
| "image_size": 64, | ||
| "num_channels": 384, | ||
| "num_res_blocks": 3, | ||
| "channel_mult": "", | ||
| "num_heads": 1, | ||
| "num_head_channels": 64, | ||
| "num_heads_upsample": -1, | ||
| "attention_resolutions": "32,16,8", | ||
| "dropout": 0, | ||
| "model_dim": 768, | ||
| "use_scale_shift_norm": True, | ||
| "resblock_updown": True, | ||
| "use_fp16": True, | ||
| "cache_text_emb": True, | ||
| "text_encoder_in_dim1": 1024, | ||
| "text_encoder_in_dim2": 768, | ||
| "image_encoder_in_dim": 768, | ||
| "num_image_embs": 10, | ||
| "pooling_type": "from_model", | ||
| "in_channels": 4, | ||
| "out_channels": 8, | ||
| "use_flash_attention": False, | ||
| }, | ||
| "diffusion_config": { | ||
| "learn_sigma": True, | ||
| "sigma_small": False, | ||
| "steps": 1000, | ||
| "noise_schedule": "linear", | ||
| "timestep_respacing": "", | ||
| "use_kl": False, | ||
| "predict_xstart": False, | ||
| "rescale_timesteps": True, | ||
| "rescale_learned_sigmas": True, | ||
| "linear_start": 0.00085, | ||
| "linear_end": 0.012, | ||
| }, | ||
| } |
Oops, something went wrong.