...
Test 1 - Different seed variations
Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling
Parameters: Steps: 50| Size: 1024x1024| Seed: 1972235878| CFG scale: 6| App: SD.Next| Version: 7ccb9d3| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: sd_xl_base_1.0| Model hash: 31e35c80fc
Time: 4m 15.88s | total 494.75 pipeline 249.02 preview 238.10 decode 5.90 move 0.69 prompt 0.61 gc 0.57 post 0.27 | GPU 9470 MB 7% | RAM 2.84 GB 2%
CFG 6, 50 STEPS | 2899868740 | 2561095516 | 3977700936 | 1099727609 | 1972235878 |
|---|---|---|---|---|---|
bookshop girl |
|
|
|
|
|
1024 |
|
|
|
|
|
face and hand 768px |
|
|
|
|
|
legs and shoes 768px |
|  |  |
|
|
...
Time: 46.40s | total 87.23 pipeline 42.72 preview 39.91 decode 2.54 move 0.89 prompt 0.88 gc 0.50 | GPU 8878 MB 7% | RAM 2.86 GB 2%
| 16 | 20 | 32 | 50 | |
|---|---|---|---|---|
CFG4 |
|
|
|
|
CFG6 |
|
|
|
|
CFG8 |
|
|
|
|
CFG10 |
|
|
|
|
CFG12 |
|
|
|
|
CFG14 |
|
|
|
|
System info
| Code Block |
|---|
app: sdnext.git updated: 2025-07-25 hash: 0b8001c0 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:122.5 used:2.83 total:125.33 xformers: diffusers: 0.35.0.dev0 transformers: 4.53.2 active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16 base: sd_xl_base_1.0 [31e35c80fc] refiner: none vae: none te: none unet: none |
...
| Code Block |
|---|
Model: sd_xl_base_1.0 Type: sdxl Class: StableDiffusionXLPipeline Size: 6 938 078 334 bytes Modified: 2025-07-15 13:47:33 |
| Module | Class | Device | DType | Params | Modules | Config |
|---|---|---|---|---|---|---|
vae | AutoencoderKL | xpu:0 | torch.bfloat16 | 83653863 | 243 | 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', 'use_quant_conv', 'use_post_quant_conv', 'latents_mean', 'shift_factor'], '_class_name': 'AutoencoderKL', '_diffusers_version': '0.20.0.dev0', '_name_or_path': '../sdxl-vae/'}) |
text_encoder | CLIPTextModel | xpu:0 | torch.bfloat16 | 123060480 | 152 | CLIPTextConfig { "architectures": [ "CLIPTextModel" ], "attention_dropout": 0.0, "bos_token_id": 0, "dropout": 0.0, "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, "torch_dtype": "float16", "transformers_version": "4.53.2", "vocab_size": 49408 } |
text_encoder_2 | CLIPTextModelWithProjection | xpu:0 | torch.bfloat16 | 694659840 | 393 | CLIPTextConfig { "architectures": [ "CLIPTextModelWithProjection" ], "attention_dropout": 0.0, "bos_token_id": 0, "dropout": 0.0, "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, "torch_dtype": "float16", "transformers_version": "4.53.2", "vocab_size": 49408 } |
tokenizer | CLIPTokenizer | None | None | 0 | 0 | None |
tokenizer_2 | CLIPTokenizer | None | None | 0 | 0 | None |
unet | UNet2DConditionModel | xpu:0 | torch.bfloat16 | 2567463684 | 1930 | FrozenDict({'sample_size': 128, 'in_channels': 4, 'out_channels': 4, 'center_input_sample': False, |
scheduler | EulerDiscreteScheduler | None | None | 0 | 0 | FrozenDict({'num_train_timesteps': 1000, 'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'scaled_linear', 'trained_betas': None, 'prediction_type': 'epsilon', 'interpolation_type': 'linear', 'use_karras_sigmas': False, 'use_exponential_sigmas': False, 'use_beta_sigmas': False, 'sigma_min': None, 'sigma_max': None, 'timestep_spacing': 'leading', 'timestep_type': 'discrete', 'steps_offset': 1, 'rescale_betas_zero_snr': False, 'final_sigmas_type': 'zero', '_use_default_values': ['use_exponential_sigmas', 'timestep_type', 'sigma_min', 'final_sigmas_type', 'use_beta_sigmas', 'sigma_max', 'rescale_betas_zero_snr'], '_class_name': 'EulerDiscreteScheduler', '_diffusers_version': '0.19.0.dev0', 'clip_sample': False, 'sample_max_value': 1.0, 'set_alpha_to_one': False, 'skip_prk_steps': True}) |
image_encoder | NoneType | None | None | 0 | 0 | None |
feature_extractor | NoneType | None | None | 0 | 0 | None |
force_zeros_for_empty_prompt | bool | None | None | 0 | 0 | None |
_class_name | str | None | None | 0 | 0 | None |
_diffusers_version | str | None | None | 0 | 0 | None |
| Code Block |
|---|
{
modelspec.sai_model_spec: "1.0.0",
modelspec.architecture: "stable-diffusion-xl-v1-base",
modelspec.implementation: "https://github.com/Stability-AI/generative-models",
modelspec.title: "Stable Diffusion XL 1.0 Base",
modelspec.author: "StabilityAI",
modelspec.description: "SDXL 1.0 Base Model, compositional expert. SDXL, the most advanced development in the Stable Diffusion text-to-image suite of models. SDXL produces massively improved image and composition detail over its predecessors. The ability to generate hyper-realistic creations for films, television, music, and instructional videos, as well as offering advancements for design and industrial use, places SDXL at the forefront of real world applications for AI imagery.",
modelspec.date: "2023-07-26",
modelspec.resolution: "1024x1024",
modelspec.prediction_type: "epsilon",
modelspec.license: "CreativeML Open RAIL++-M License",
modelspec.thumbnail: "data",
modelspec.hash_sha256: "0xd7a9105a900fd52748f20725fe52fe52b507fd36bee4fc107b1550a26e6ee1d7"
} |
...