Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

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.


CFG5CFG7, STEP 28STEP30Seed: 1620085323Seed:1931701040Seed:4075624134Seed:2736029172
bookshop girl

Image Added

Image Added

Image Added

Image Added

hand and face

Image Added

Image Added

Image Added

Image Added

legs and shoes

Image Added

Image Added

Image Added

Image Added

improved prompts

Prompt: masterpiece, best quality, photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling

...

CFG5, STEP 28Seed: 1620085323Seed:1931701040Seed:4075624134Seed:2736029172
bookshop girl

Image Added

Image Added

Image Added

Image Added

hand and face

Image Added

Image Added

Image Added

Image Added

legs and shoes

Image Added

Image Added

Image Added

Image Added

Test 1 - Bookshop

romptPrompt: masterpiece, best quality, photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling

Negative: nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthroanthr

Parameters: Steps: 30| Size: 1024x1024| Seed: 4075624134| CFG scale: 42| App: SD.Next| Version: e762994d5eaed8| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: noobaiXLNAIXL_vPred10VersionepsilonPred11Version| Model hash: ea349eeae86681e8e4b1


Time: 2m 4443.63s 03s | total 187185.94 22 pipeline 158156.36 82 callback 12.38 36 preview 109.61 03 decode 6.23 17 prompt 0.47 gc 0.31 33 | GPU 9436 MB 8% | RAM 4445.95 06 GB 36%




20304050

CFG1

Image Added

Image Added

Image Added

Image Added

CFG2

Image Added

Image Added

Image Added

Image Added

CFG3

Image Added

Image Added

Image Added

Image Added

CFG4

Image Added

Image Added

Image Added

Image Added

CFG5

Image Added

Image Added

Image Added

Image Added

CFG6

Image Added

Image Added

Image Added

Image Added

CFG7

Image Added

Image Added

Image Added

Image Added

CFG8

Image Added

Image Added

Image Added

Image Added

CFG9

Image Added

Image Added

Image Added

Image Added


Test 2 - Face and hand

Prompt: masterpiece, best quality, 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.

Negative: nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthro, furry, ambiguous form, feral, semi-anthroanthr

Parameters: Steps: 32| Size: 1024x1024| Seed: 27360291721620085323| CFG scale: 49| App: SD.Next| Version: e762994d5eaed8| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: noobaiXLNAIXL_vPred10VersionepsilonPred11Version| Model hash: ea349eeae86681e8e4b1


Time: 2m 5550.81s 55s | total 197188.72 15 pipeline 169164.41 37 callback 13.25 preview 7.51 23 decode 6.36 prompt 0.82 14 preview 4.06 gc 0.32 | GPU 9436 9438 MB 8% | RAM 4445.99 29 GB 36%



8162032

CFG1

Image Added

Image Added

Image Added

Image Added

CFG2

Image Added

Image Added

Image Added

Image Added

CFG3

Image Added

Image Added

Image Added

Image Added

CFG4

Image Added

Image Added

Image Added

Image Added

CFG5

Image Added

Image Added

Image Added

Image Added

CFG6

Image Added

Image Added

Image Added

Image Added

CFG8

Image Added

Image Added

Image Added

Image Added

CFG9

Image Added

Image Added

Image Added

Image Added

Test 3 - Legs

Prompt: masterpiece, best quality, 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.

Negative: nsfw, worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, mammal, anthroanthropoid, furry, ambiguous form, feral, semi-anthro

Parameters: Steps: 32| Size: 1024x1024| Seed: 19317010402736029172| CFG scale: 35| App: SD.Next| Version: 3e105f3d5eaed8| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: noobaiXLNAIXL_vPred10VersionepsilonPred11Version| Model hash: ea349eeae86681e8e4b1


Time: 3m 502m 53.46s 66s | total 190193.37 44 pipeline 166167.10 47 callback 13.21 23 decode 6.34 14 preview 35.48 41 prompt 0.80 gc 0.41 34 | GPU 9442 9434 MB 8% | RAM 2144.42 98 GB 17%36%



8162032

CFG1

Image Added

Image Added

Image Added

Image Added

CFG2

Image Added

Image Added

Image Added

Image Added

CFG3

Image Added

CFG4

CFG4.5

CFG5

CFG8

Image Added

Image Added

Image Added

CFG4

Image Added

Image Added

Image Added

Image Added

CFG5

Image Added

Image Added

Image Added

Image Added

CFG6

Image Added

Image Added

Image Added

Image Added

CFG7

Image Added

Image Added

Image Added

Image Added

CFG8

Image Added

Image Added

Image Added

Image Added

CFG9

Image Added

Image Added

Image Added

Image Added

Test 4 - Other model Covers

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added

System info


Code Block
Wed OctNov 2912 1921:0723:2724 2025
app: sdnext.git updated: 2025-1011-2911 hash: 3e105f34cd5eaed811 url: https://github.com/liutyi/sdnext.git/tree/ipex
arch: x86_64 cpu: x86_64 system: Linux release: 6.14.0-3335-generic 
python: 3.12.3 Torch: 2.7.1+xpu
device: Intel(R) Arc(TM) Graphics (1) ipex: 2.7.10+xpu
ram: free:120102.9811 used:423.3522 total:125.33
gpu: free:106108.95 used:108.4787 total:117.37 gpu-active: current:6.7275 peak:8.3409 gpu-allocated: current:6.7275 peak:8.3409 gpu-reserved: current:108.4787 peak:108.4787 gpu-inactive: current:0.587 peak:10.1591
events: retries:0 oom:0 utilization: 0
xformers: diffusers: 0.36.0.dev0 transformers: 4.57.1
active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16 bfloat16 
base: noobaiXLNAIXL_vPred10VersionepsilonPred11Version [6681e8e4b1] refiner: none vae: none te: none unet: none


Config

Code Block
{
  "sd_model_checkpoint": "noobaiXLNAIXL_epsilonPred11Version [6681e8e4b1]",
  "diffusers_to_gpu": true,
  "device_map": "gpu",
  "diffusers_offload_mode": "none",
  "sdnq_dequantize_compile": false,
  "ui_request_timeout": 300000,
  "huggingface_token": "hf_...FraU",
  "diffusers_version": "b3e9dfced7c9e8d00f646c710766b532383f04c6",
  "sd_checkpoint_hash": "ea349eeae87ca8d25ba902c93810f7ca83e5c82f920edf12f273af004ae02819",
  "civitai_token": "xxx"
}


Model info

noobaiXLNAIXL_vPred10Version epsilonPred11Version [ea349eeae86681e8e4b1]

ModuleClassDeviceDtypeQuantParamsModulesConfig
vaeAutoencoderKLxpu:0torch.bfloat16None83653863243

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, 256, 512, 512], 'layers_per_block': 2, 'act_fn': 'silu', 'latent_channels': 4, 'norm_num_groups': 32, 'sample_size': 1024, 'scaling_factor': 0.13025, 'shift_factor': None, 'latents_mean': None, 'latents_std': None, 'force_upcast': False, 'use_quant_conv': True, 'use_post_quant_conv': True, 'mid_block_add_attention': True, '_use_default_values': ['mid_block_add_attention', 'latents_std', 'shift_factor', 'use_post_quant_conv', 'latents_mean', 'use_quant_conv'], '_class_name': 'AutoencoderKL', '_diffusers_version': '0.20.0.dev0', '_name_or_path': '../sdxl-vae/'})

text_encoderCLIPTextModelxpu:0torch.bfloat16None123060480152

CLIPTextConfig { "architectures": [ "CLIPTextModel" ], "attention_dropout": 0.0, "bos_token_id": 0, "dropout": 0.0, "dtype": "float16", "eos_token_id": 2, "hidden_act": "quick_gelu", "hidden_size": 768, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "projection_dim": 768, "transformers_version": "4.57.1", "vocab_size": 49408 }

text_encoder_2CLIPTextModelWithProjectionxpu:0torch.bfloat16None694659840393

CLIPTextConfig { "architectures": [ "CLIPTextModelWithProjection" ], "attention_dropout": 0.0, "bos_token_id": 0, "dropout": 0.0, "dtype": "float16", "eos_token_id": 2, "hidden_act": "gelu", "hidden_size": 1280, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 5120, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "num_attention_heads": 20, "num_hidden_layers": 32, "pad_token_id": 1, "projection_dim": 1280, "transformers_version": "4.57.1", "vocab_size": 49408 }

tokenizerCLIPTokenizerNoneNoneNone00

None

tokenizer_2CLIPTokenizerNoneNoneNone00

None

unetUNet2DConditionModelxpu:0torch.bfloat16None25674636841930

FrozenDict({'sample_size': 128, 'in_channels': 4, 'out_channels': 4, 'center_input_sample': False, 'flip_sin_to_cos': True, 'freq_shift': 0, 'down_block_types': ['DownBlock2D', 'CrossAttnDownBlock2D', 'CrossAttnDownBlock2D'], 'mid_block_type': 'UNetMidBlock2DCrossAttn', 'up_block_types': ['CrossAttnUpBlock2D', 'CrossAttnUpBlock2D', 'UpBlock2D'], 'only_cross_attention': False, 'block_out_channels': [320, 640, 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': 2048, 'transformer_layers_per_block': [1, 2, 10], 'reverse_transformer_layers_per_block': None, 'encoder_hid_dim': None, 'encoder_hid_dim_type': None, 'attention_head_dim': [5, 10, 20], 'num_attention_heads': None, 'dual_cross_attention': False, 'use_linear_projection': True, 'class_embed_type': None, 'addition_embed_type': 'text_time', 'addition_time_embed_dim': 256, 'num_class_embeds': None, 'upcast_attention': None, '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': 2816, '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': ['dropout', 'attention_type', 'reverse_transformer_layers_per_block'], '_class_name': 'UNet2DConditionModel', '_diffusers_version': '0.19.0.dev0'})

schedulerEulerAncestralDiscreteSchedulerNoneNoneNone00

FrozenDict({'num_train_timesteps': 1000, 'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'scaled_linear', 'trained_betas': None, 'prediction_type': 'epsilon', 'timestep_spacing': 'trailing', 'steps_offset': 1, 'rescale_betas_zero_snr': False, 'interpolation_type': 'linear', 'use_karras_sigmas': False, '_class_name': 'EulerAncestralDiscreteScheduler', '_diffusers_version': '0.35.1', 'clip_sample': False, 'sample_max_value': 1.0, 'set_alpha_to_one': False, 'skip_prk_steps': True})

image_encoderNoneTypeNoneNoneNone00

None

feature_extractorNoneTypeNoneNoneNone00

None

force_zeros_for_empty_promptboolNoneNoneNone00

None