Info
https://huggingface.co/Photoroom/prx-1024-t2i-beta
Prompt: A delicate, golden origami boat rests serenely on the surface of calm, shallow water, its crisp folds catching the warm, golden light of either sunrise or sunset. The paper vessel, crafted with precision, glides effortlessly across the gentle ripples, its reflection mirrored perfectly in the still water below — a symmetrical, shimmering star-like shape that doubles the beauty of the scene. The background dissolves into a soft, dreamy blur of sky and distant greenery, with clouds painted in soft hues of blue and gold, enhancing the tranquil, almost meditative atmosphere. The scene evokes a sense of quiet journey, hope, and the gentle passage of time — a simple paper boat carrying a silent promise across the liquid mirror of the world.
Parameters: Steps: 28| Size: 1024x1024| Seed: 1868265953| CFG scale: 6| App: SD.Next| Version: c021928| Pipeline: PRXPipeline| Operations: txt2img| Model: prx-1024-t2i-beta
Time: 4m 2.55s | total 247.57 pipeline 236.44 decode 6.09 callback 4.35 te 0.38 gc 0.28 | GPU 10152 MB 8% | RAM 18.47 GB 15%
Resolution: 1024 pixels
Architecture: PRX (MMDiT-like diffusion transformer variant)
Latent backbone: Flux's VAE
Text encoder: T5-Gemma-2B-2B-UL2
Training stage: Supervised fine-tuning (SFT)
from diffusers.pipelines.prx import PRXPipeline
pipe = PRXPipeline.from_pretrained(
"Photoroom/prx-1024-t2i-beta",
torch_dtype=torch.bfloat16
).to("cuda")
prompt = "A front-facing portrait of a lion in the golden savanna at sunset"
image = pipe(prompt, num_inference_steps=28, guidance_scale=5.0).images[0]
image.save("lion.png")
Test 0 - Different seed variations
Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling
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.
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.
| CFG5, STEP28 | Seed: 1620085323 | Seed:1931701040 | Seed:4075624134 | Seed:2736029172 |
|---|---|---|---|---|
| bookshop girl |
|
|
|
|
| hand and face |
|
|
|
|
| legs and shoes |
|
|
|
|
Test 1 - Bookshop
Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling
Parameters: Steps: 32| Size: 1024x1024| Seed: 1868265953| CFG scale: 5| App: SD.Next| Version: c021928| Pipeline: PRXPipeline| Operations: txt2img| Model: prx-1024-t2i-beta
Time: 4m 36.64s | total 282.33 pipeline 270.51 decode 6.11 callback 5.00 te 0.39 gc 0.30 | GPU 10152 MB 8% | RAM 18.46 GB 15%
| 4 | 8 | 16 | 32 | 64 | |
|---|---|---|---|---|---|
CFG1 | |||||
CFG2 | |||||
CFG3 | |||||
CFG4 | |||||
CFG5 |
| ||||
CFG6 | |||||
CFG7 | |||||
CFG8 |
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.
Parameters: Steps: 50| Size: 1024x1024| Seed: 1868265953| CFG scale: 5| App: SD.Next| Version: c021928| Pipeline: PRXPipeline| Operations: txt2img| Model: prx-1024-t2i-beta
Time: 7m 7.45s | total 436.01 pipeline 421.33 callback 7.90 decode 6.09 te 0.39 gc 0.28 | GPU 10152 MB 8% | RAM 18.47 GB 15%
| 8 | 16 | 25 | 50 | |
|---|---|---|---|---|
CFG1 | ||||
CFG2 | ||||
CFG3 | ||||
CFG4 | ||||
CFG5 |
| |||
CFG6 | ||||
CFG7 | ||||
CFG8 | ||||
CFG10 |
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.
| 8 | 16 | 25 | 50 | |
|---|---|---|---|---|
CFG1 | ||||
CFG2 | ||||
CFG3 | ||||
CFG4 | ||||
CFG5 | ||||
CFG6 | ||||
CFG8 | ||||
CFG10 |
Test 4 - Other model Covers
Test 5 - Art collection
https://civitai.com/collections/10716337
Test 6 - Model own example prompts
System info
Sat Nov 15 10:36:54 2025 app: sdnext.git updated: 2025-11-14 hash: c02192870 url: https://github.com/liutyi/sdnext/tree/pytorch arch: x86_64 cpu: x86_64 system: Linux release: 6.14.0-35-generic python: 3.12.3 torch 2.9.1+xpu device: Intel(R) Arc(TM) Graphics (1) ipex: ram: free:121.86 used:3.47 total:125.33 xformers: diffusers: 0.36.0.dev0 transformers: 4.57.1 active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16 base: Diffusers/Photoroom/prx-1024-t2i-beta [318a05beb7] refiner: none vae: none te: none unet: none
Config
{
}
Model info
Diffusers/Photoroom/prx-1024-t2i-beta [318a05beb7]
| Module | Class | Device | Dtype | Quant | Params | Modules | Config |
|---|---|---|---|---|---|---|---|
| transformer | PRXTransformer2DModel | xpu:0 | torch.bfloat16 | None | 1170691648 | 303 | FrozenDict({'in_channels': 16, 'patch_size': 2, 'context_in_dim': 2304, 'hidden_size': 1792, 'mlp_ratio': 3.5, 'num_heads': 28, 'depth': 16, 'axes_dim': [32, 32], 'theta': 10000, 'time_factor': 1000.0, 'time_max_period': 10000, '_name_or_path': 'Photoroom/prx-1024-t2i-beta'}) |
| scheduler | FlowMatchEulerDiscreteScheduler | None | None | None | 0 | 0 | FrozenDict({'num_train_timesteps': 1000, 'shift': 3.0, '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': ['use_karras_sigmas', 'use_exponential_sigmas', 'max_image_seq_len', 'use_beta_sigmas', 'time_shift_type', 'shift_terminal', 'use_dynamic_shifting', |
| text_encoder | T5GemmaEncoder | xpu:0 | torch.bfloat16 | None | 2614341888 | 448 | T5GemmaConfig { "architectures": [ "T5GemmaEncoder" ], "attention_bias": false, "attention_dropout": 0.0, "attn_logit_softcapping": 50.0, "bos_token_id": 2, "classifier_dropout_rate": 0.0, "decoder": { "attention_bias": false, "attention_dropout": 0.0, "attn_logit_softcapping": 50.0, "cross_attention_hidden_size": 2304, "dropout_rate": 0.0, "final_logit_softcapping": 30.0, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 2304, "initializer_range": 0.02, "intermediate_size": 9216, "is_decoder": true, "layer_types": [ "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 8192, "model_type": "t5_gemma_module", "num_attention_heads": 8, "num_hidden_layers": 26, "num_key_value_heads": 4, "query_pre_attn_scalar": 256, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "use_cache": true, "vocab_size": 256000 }, "dropout_rate": 0.0, "dtype": "bfloat16", "encoder": { "attention_bias": false, "attention_dropout": 0.0, "attn_logit_softcapping": 50.0, "dropout_rate": 0.0, "final_logit_softcapping": 30.0, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 2304, "initializer_range": 0.02, "intermediate_size": 9216, "layer_types": [ "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 8192, "model_type": "t5_gemma_module", "num_attention_heads": 8, "num_hidden_layers": 26, "num_key_value_heads": 4, "query_pre_attn_scalar": 256, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "use_cache": true, "vocab_size": 256000 }, "eos_token_id": 1, "final_logit_softcapping": 30.0, "head_dim": 256, "hidden_activation": "gelu_pytorch_tanh", "hidden_size": 2304, "initializer_range": 0.02, "intermediate_size": 9216, "is_encoder_decoder": true, "layer_types": [ "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 8192, "model_type": "t5gemma", "num_attention_heads": 8, "num_hidden_layers": 26, "num_key_value_heads": 4, "pad_token_id": 0, "query_pre_attn_scalar": 256, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "sliding_window": 4096, "transformers_version": "4.57.1", "use_cache": true, "vocab_size": 256000 } |
| tokenizer | GemmaTokenizerFast | None | None | None | 0 | 0 | None |
| vae | AutoencoderKL | xpu:0 | torch.bfloat16 | None | 83819683 | 241 | 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': 16, 'norm_num_groups': 32, 'sample_size': 1024, 'scaling_factor': 0.3611, 'shift_factor': 0.1159, 'latents_mean': None, 'latents_std': None, 'force_upcast': True, 'use_quant_conv': False, 'use_post_quant_conv': False, 'mid_block_add_attention': True, '_class_name': 'AutoencoderKL', '_diffusers_version': '0.36.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--Photoroom--prx-1024-t2i-beta/snapshots/318a05beb7d65d55616e8fc17b325055be0e4756/vae'}) |
| default_sample_size | int | None | None | None | 0 | 0 | None |
