Info

https://huggingface.co/stabilityai/stable-diffusion-2-1-base

Test 1 - Different seed variations

Check different seed impacts on the result

Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling

Execution: Time: 3m 31.25s | total 250.27 pipeline 207.28 preview 38.56 decode 3.49 gc 0.60 post 0.25 | GPU 3444 MB 3% | RAM 2.96 GB 2%

2899868740

2561095516

3977700936

1099727609

1972235878

bookshop girl

face and hand

CFG 6

50 STEPS

legs and shoes

Test 1 - Bookshop

Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling

Execution: Time: 2m 16.41s | total 160.46 pipeline 132.67 preview 23.83 decode 3.48 gc 0.58 | GPU 3444 MB 3% | RAM 2.98 GB 2%

	8	16	20	32	50
CFG0 CFG1
CFG2
CFG3
CFG4
CFG5
CFG6
CFG7
CFG8
CFG9

Test 2 - Face and hand

Prompt: Create a close-up photograph of a woman's face and hand, with her hand raised to her chin. She is wearing a white blazer and has a gold ring on her finger. Her nails are neatly manicured and her hair is pulled back into a low bun. She is smiling and has a radiant expression on her face. The background is a plain light gray color. The overall mood of the photo is elegant and sophisticated. The photo should have a soft, natural light and a slight warmth to it. The woman's hair is dark brown and pulled back into a low bun, with a few loose strands framing her face.

	8	16	20	32	50	100
CFG0 CFG1
CFG2
CFG3
CFG4
6
8
12

Test 3 - Legs

Prompt: Generate a photo of a woman's legs, with her feet crossed and wearing white high-heeled shoes with ribbons tied around her ankles. The shoes should have a pointed toe and a stiletto heel. The woman's legs should be smooth and tanned, with a slight sheen to them. The background should be a light gray color. The photo should be taken from a low angle, looking up at the woman's legs. The ribbons should be tied in a bow shape around the ankles. The shoes should have a red sole. The woman's legs should be slightly bent at the knee.

Parameters: Time: 3m 32.10s | total 249.31 pipeline 208.00 preview 36.62 decode 3.49 gc 0.59 move 0.36 prompt 0.33 | GPU 3444 MB 3% | RAM 2.97 GB 2%

	8	16	20	32	50
CFG0 CFG1
CFG2
CFG3
CFG4
6
8
12

System info

app: sdnext.git updated: 2025-07-20 hash: 287c3600 url: https://github.com/vladmandic/sdnext.git/tree/dev
arch: x86_64 cpu: x86_64 system: Linux release: 6.14.0-24-generic
python: 3.12.3 Torch 2.7.1+xpu
device: Intel(R) Arc(TM) Graphics (1) ipex: 
ram: free:122.37 used:2.96 total:125.33
xformers:  diffusers: 0.35.0.dev0 transformers: 4.53.2
active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16
Cross-attention: Scaled-Dot-Product

Model Info

Module	Class	Device	DType	Params	Modules	Config
tokenizer	CLIPTokenizer	None	None	0	0	None
unet	UNet2DConditionModel	xpu:0	torch.bfloat16	865910724	709	FrozenDict({'sample_size': 96, 'in_channels': 4, 'out_channels': 4, 'center_input_sample': False, 'flip_sin_to_cos': True, 'freq_shift': 0, 'down_block_types': ['CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'DownBlock2D'], 'mid_block_type': 'UNetMidBlock2DCrossAttn', 'up_block_types': ['UpBlock2D', 'CrossAttnUpBlock2D', 'CrossAttnUpBlock2D', 'CrossAttnUpBlock2D'], 'only_cross_attention': False, 'block_out_channels': [320, 640, 1280, 1280], 'layers_per_block': 2, 'downsample_padding': 1, 'mid_block_scale_factor': 1, 'dropout': 0.0, 'act_fn': 'silu', 'norm_num_groups': 32, 'norm_eps': 1e-05, 'cross_attention_dim': 1024, 'transformer_layers_per_block': 1, 'reverse_transformer_layers_per_block': None, 'encoder_hid_dim': None, 'encoder_hid_dim_type': None, 'attention_head_dim': [5, 10, 20, 20], 'num_attention_heads': None, 'dual_cross_attention': False, 'use_linear_projection': True, 'class_embed_type': None, 'addition_embed_type': None, 'addition_time_embed_dim': None, 'num_class_embeds': None, 'upcast_attention': True, 'resnet_time_scale_shift': 'default', 'resnet_skip_time_act': False, 'resnet_out_scale_factor': 1.0, 'time_embedding_type': 'positional', 'time_embedding_dim': None, 'time_embedding_act_fn': None, 'timestep_post_act': None, 'time_cond_proj_dim': None, 'conv_in_kernel': 3, 'conv_out_kernel': 3, 'projection_class_embeddings_input_dim': None, 'attention_type': 'default', 'class_embeddings_concat': False, 'mid_block_only_cross_attention': None, 'cross_attention_norm': None, 'addition_embed_type_num_heads': 64, '_use_default_values': ['cross_attention_norm', 'transformer_layers_per_block', 'timestep_post_act', 'num_attention_heads', 'addition_time_embed_dim', 'resnet_time_scale_shift', 'reverse_transformer_layers_per_block', 'time_embedding_type', 'class_embed_type', 'time_embedding_act_fn', 'addition_embed_type', 'attention_type', 'class_embeddings_concat', 'mid_block_type', 'time_cond_proj_dim', 'encoder_hid_dim_type', 'addition_embed_type_num_heads', 'resnet_skip_time_act', 'mid_block_only_cross_attention', 'resnet_out_scale_factor', 'conv_in_kernel', 'dropout', 'conv_out_kernel', 'projection_class_embeddings_input_dim', 'encoder_hid_dim', 'time_embedding_dim'], '_class_name': 'UNet2DConditionModel', '_diffusers_version': '0.10.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/unet'})
scheduler	DDIMScheduler	None	None	0	0	FrozenDict({'num_train_timesteps': 1000, 'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'scaled_linear', 'trained_betas': None, 'clip_sample': False, 'set_alpha_to_one': False, 'steps_offset': 1, 'prediction_type': 'v_prediction', 'thresholding': False, 'dynamic_thresholding_ratio': 0.995, 'clip_sample_range': 1.0, 'sample_max_value': 1.0, 'timestep_spacing': 'leading', 'rescale_betas_zero_snr': False, '_use_default_values': ['clip_sample_range', 'thresholding', 'timestep_spacing', 'dynamic_thresholding_ratio', 'rescale_betas_zero_snr', 'sample_max_value'], '_class_name': 'DDIMScheduler', '_diffusers_version': '0.8.0', 'skip_prk_steps': True})
safety_checker	NoneType	None	None	0	0	None
feature_extractor	CLIPImageProcessor	None	None	0	0	None
image_encoder	NoneType	None	None	0	0	None
requires_safety_checker	bool	None	None	0	0	None
_name_or_path	str	None	None	0	0	None
_class_name	str	None	None	0	0	None
_diffusers_version	str	None	None	0	0	None

Page tree

Test 30 - Stable Diffusion 2.1 - steps and guidance