Info
https://huggingface.co/purplesmartai/pony-v7-base
| Code Block |
|---|
V7 supportsbased on Auraflow. Supports resolutions in the range of 768px to 1536px. It is recommended to go for higher resolutions and at least 30 steps during inference. Both positive and negative prompts with special tags (see the end of the article) is recommended. |
Test 0 - Different seed variations
Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling
...
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.
1280 vs 1024 vs 768
| CFG5, STEP 50 | Seed: 1620085323 | Seed:1931701040 | Seed:4075624134 | Seed:2736029172 |
|---|---|---|---|---|
bookshop girl 1024px | hand and face | legs and shoes |
1024
|
|
|
| |
bookshop girl 1280px |
|
|
| |
| CFG6, STEP 12 | Seed: 1620085323 | Seed:1931701040 | Seed:4075624134 | Seed:2736029172 |
|---|---|---|---|---|
hand and face | legs and shoes |
Test 1 - Bookshop
Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling
...
CFG1
...
CFG2
...
CFG3
...
CFG4
...
CFG5
...
CFG6
...
CFG8
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.
...
CFG1
...
CFG2
...
CFG3
...
CFG3.5
...
CFG4
...
CFG5
...
CFG8
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.
...
CFG1
...
CFG2
...
CFG3
...
CFG3.5
...
CFG4
...
CFG5
...
CFG8
Test 4 - Other model Covers
...
1024px |
|
|
|
|
hand and face 1280px |
|
|
|
adjusted prompts (score_9 ...) |
legs and shoes 1024px |
|
|
|
|
legs and shoes 1280px |
|
|
|
|
System info
| Code Block |
|---|
Tue Oct 28 19:05:13 2025 app: sdnext.git updated: 2025-10-28 hash: 913af5ebf url: https://github.com/liutyi/sdnext.git/tree/ipex arch: x86_64 cpu: x86_64 system: Linux release: 6.14.0-33-generic python: 3.12.3 Torch 2.7.1+xpu device: Intel(R) Arc(TM) Graphics (1) ipex: 2.7.10+xpu ram: free:121.31 used:4.02 total:125.33 gpu: free:98.06 used:19.31 total:117.37 gpu-active: current:15.57 peak:17.28 gpu-allocated: current:15.57 peak:17.28 gpu-reserved: current:19.31 peak:19.31 gpu-inactive: current:0.43 peak:0.91 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 base: Diffusers/purplesmartai/pony-v7-base [af688af595] refiner: none vae: none te: none unet: none ipex native none Scaled-Dot-Product |
Config
| Code Block |
|---|
{
"diffusers_version": "84e16575e4c5e90b6b49301cfa162ced4cf478d2",
"diffusers_to_gpu": true,
"device_map": "gpu",
"model_wan_stage": "combined",
"diffusers_offload_mode": "none",
"ui_request_timeout": 300000,
"civitai_token": "f1..65",
"huggingface_token": "hf_...FraU",
"hf_transfer_mode": "xet",
"sd_checkpoint_hash": null,
"sdnq_dequantize_compile": false,
"show_progress_type": "Approximate",
"sd_model_checkpoint": "Diffusers/purplesmartai/pony-v7-base [af688af595]"
} |
Model info
| Module | Class | Device | Dtype | Quant | Params | Modules | Config |
|---|---|---|---|---|---|---|---|
| tokenizer | LlamaTokenizerFast | None | None | None | 0 | 0 | None |
| text_encoder | UMT5EncoderModel | xpu:0 | torch.bfloat16 | None | 1223550976 | 486 | UMT5Config { "architectures": [ "UMT5EncoderModel" ], "classifier_dropout": 0.0, "d_ff": 5120, "d_kv": 64, "d_model": 2048, "decoder_start_token_id": 0, "dense_act_fn": "gelu_new", "dropout_rate": 0.1, "dtype": "bfloat16", "eos_token_id": 2, "feed_forward_proj": "gated-gelu", "initializer_factor": 1.0, "is_encoder_decoder": true, "is_gated_act": true, "layer_norm_epsilon": 1e-06, "model_type": "umt5", "num_decoder_layers": 24, "num_heads": 32, "num_layers": 24, "output_past": true, "pad_token_id": 0, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "scalable_attention": true, "tie_word_embeddings": false, "tokenizer_class": "LlamaTokenizerFast", "transformers_version": "4.57.1", "use_cache": true, "vocab_size": 32128 } |
| vae | AutoencoderKL | xpu:0 | torch.bfloat16 | None | 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': True, 'use_quant_conv': True, 'use_post_quant_conv': True, 'mid_block_add_attention': True, '_use_default_values': ['mid_block_add_attention'], '_class_name': 'AutoencoderKL', '_diffusers_version': '0.30.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--purplesmartai--pony-v7-base/snapshots/af688af595b3ed4d482e2997a0804250a06a9e8f/vae'}) |
| transformer | AuraFlowTransformer2DModel | xpu:0 | torch.bfloat16 | None | 6858605568 | 759 | FrozenDict({'sample_size': 64, 'patch_size': 2, 'in_channels': 4, 'num_mmdit_layers': 4, 'num_single_dit_layers': 32, 'attention_head_dim': 256, 'num_attention_heads': 12, 'joint_attention_dim': 2048, 'caption_projection_dim': 3072, 'out_channels': 4, 'pos_embed_max_size': 9216, '_class_name': 'AuraFlowTransformer2DModel', '_diffusers_version': '0.34.0.dev0', '_name_or_path': 'purplesmartai/pony-v7-base'}) |
| scheduler | FlowMatchEulerDiscreteScheduler | None | None | None | 0 | 0 | FrozenDict({'num_train_timesteps': 1000, 'shift': 1.73, 'use_dynamic_shifting': False, 'base_shift': 0.5, 'max_shift': 1.15, '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': 'exponential', 'stochastic_sampling': False, '_use_default_values': ['invert_sigmas', 'shift_terminal', 'use_exponential_sigmas', 'use_dynamic_shifting', 'stochastic_sampling', 'max_image_seq_len', 'base_image_seq_len', 'max_shift', 'use_beta_sigmas', 'base_shift', |
Prompting Pony V7
https://civitai.com/articles/21107
...