...
Test
| STEP:4 | 8 | 16 | 20 | 32 | |
|---|---|---|---|---|---|
| CFG:1 |
|
|
|
|
|
| 2 |
|
|
|
|
|
| 3 |
|
|
|
|
|
| 4 |
|
|
|
|
|
| 6 |
|
|
|
|
|
| 8 |
|
|
System
| Code Block |
|---|
app: sdnext.git updated: 2025-07-18 hash: 4ef0a4d5 url: https://github.com/vladmandic/sdnext.git/tree/dev arch: x86_64 cpu: x86_64 system: Linux release: 6.11.0-29-generic python: 3.12.3 2.7.1+xpu device: Intel(R) Arc(TM) Graphics (1) ipex: ram: free:123.65 used:1.68 total:125.33 xformers: diffusers: 0.35.0.dev0 transformers: 4.53.2 active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16 |
...
Module | Class | Device | DType | Params | Modules | Config |
|---|---|---|---|---|---|---|
tokenizer | PreTrainedTokenizerFast | None | None | 0 | 0 | None |
text_encoder | GlmForCausalLM | xpu:0 | torch.bfloat169399951360 | 9399951360 | 487 | GlmConfig { "architectures": [ "GlmModel" ], "attention_bias": true, "attention_dropout": 0.0, "eos_token_id": [ 151329, 151336, 151338 ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 13696, "max_position_embeddings": 8192, "model_type": "glm", "num_attention_heads": 32, "num_hidden_layers": 40, "num_key_value_heads": 2, "pad_token_id": 151329, "partial_rotary_factor": 0.5, "rms_norm_eps": 1.5625e-07, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.53.2", "use_cache": true, "vocab_size": 151552 } |
vae | AutoencoderKL | xpu:0 | torch.bfloat16 | 406100643406100643 | 281 | FrozenDict({'in_channels': 3, 'out_channels': 3, 'down_block_types': ['DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D'], 'up_block_types': ['UpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D'], 'block_out_channels': [128, 512, 1024, 1024], 'layers_per_block': 3, 'act_fn': 'silu', 'latent_channels': 16, 'norm_num_groups': 32, 'sample_size': 1024, 'scaling_factor': 1.0, 'shift_factor': 0.0, 'latents_mean': None, 'latents_std': None, 'force_upcast': True, 'use_quant_conv': False, 'use_post_quant_conv': False, 'mid_block_add_attention': False, '_class_name': 'AutoencoderKL', '_diffusers_version': '0.33.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--THUDM--CogView4-6B/snapshots/63a52b7f6dace7033380cd6da14d0915eab3e6b5/vae'}) |
transformer | CogView4Transformer2DModel | xpu:0 | torch.bfloat166369118272 | 6369118272 | 638 | FrozenDict({'patch_size': 2, 'in_channels': 16, 'out_channels': 16, 'num_layers': 28, 'attention_head_dim': 128, 'num_attention_heads': 32, 'text_embed_dim': 4096, 'time_embed_dim': 512, 'condition_dim': 256, 'pos_embed_max_size': 128, 'sample_size': 128, 'rope_axes_dim': [256, 256], '_class_name': 'CogView4Transformer2DModel', '_diffusers_version': '0.33.0.dev0', '_name_or_path': 'THUDM/CogView4-6B'}) |
scheduler | FlowMatchEulerDiscreteScheduler | None | None | 0 | 0 | FrozenDict({'num_train_timesteps': 1000, 'shift': 1.0, 'use_dynamic_shifting': True, 'base_shift': 0.25, 'max_shift': 0.75, 'base_image_seq_len': 256, 'max_image_seq_len': 4096, 'invert_sigmas': False, 'shift_terminal': None, 'use_karras_sigmas': False, 'use_exponential_sigmas': False, 'use_beta_sigmas': False, 'time_shift_type': 'linear', 'stochastic_sampling': False, '_use_default_values': ['stochastic_sampling'], '_class_name': 'FlowMatchEulerDiscreteScheduler', '_diffusers_version': '0.33.0.dev0'}) |
_name_or_path | str | None | None | 0 | 0 | None |
...