andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

WIP support for Nvidia Cosmos 7B and 14B text to world (video) models.

Browse Source
This commit is contained in:
comfyanonymous
2025-01-10 09:11:57 -05:00
parent 129d8908f7
commit 2ff3104f70
16 changed files with 3383 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
comfy/text_encoders/t5_old_config_xxl.json Normal file
View File

@@ -0,0 +1,22 @@
{
"d_ff": 65536,
"d_kv": 128,
"d_model": 1024,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"dense_act_fn": "relu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": false,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 24,
"num_heads": 128,
"num_layers": 24,
"output_past": true,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"vocab_size": 32128
}