lucataco/pixart-xl-2 🔢❓📝 → 🖼️
About
PixArt-Alpha 1024px is a transformer-based text-to-image diffusion system trained on text embeddings from T5
Example Output
Prompt:
"an astronaut sitting in a diner, eating fries, cinematic, analog film"
Output
Performance Metrics
6.04s
Prediction Time
142.63s
Total Time
All Input Parameters
{
"style": "None",
"width": 1024,
"height": 1024,
"prompt": "an astronaut sitting in a diner, eating fries, cinematic, analog film",
"scheduler": "DPMSolverMultistep",
"num_outputs": 1,
"guidance_scale": 4.5,
"num_inference_steps": 14
}
Input Parameters
- seed
- Random seed. Leave blank to randomize the seed
- style
- Image style
- width
- Width of output image
- height
- Height of output image
- prompt
- Input prompt
- scheduler
- scheduler
- num_outputs
- Number of images to output.
- guidance_scale
- Scale for classifier-free guidance
- negative_prompt
- Negative prompt
- num_inference_steps
- Number of denoising steps
Output Schema
Output
Example Execution Logs
Using seed: 255397398 Prompt: an astronaut sitting in a diner, eating fries, cinematic, analog film Negative Prompt: None 0%| | 0/14 [00:00<?, ?it/s] 7%|▋ | 1/14 [00:00<00:04, 2.86it/s] 14%|█▍ | 2/14 [00:00<00:03, 3.16it/s] 21%|██▏ | 3/14 [00:00<00:03, 3.26it/s] 29%|██▊ | 4/14 [00:01<00:03, 3.29it/s] 36%|███▌ | 5/14 [00:01<00:02, 3.32it/s] 43%|████▎ | 6/14 [00:01<00:02, 3.34it/s] 50%|█████ | 7/14 [00:02<00:02, 3.35it/s] 57%|█████▋ | 8/14 [00:02<00:01, 3.36it/s] 64%|██████▍ | 9/14 [00:02<00:01, 3.36it/s] 71%|███████▏ | 10/14 [00:03<00:01, 3.36it/s] 79%|███████▊ | 11/14 [00:03<00:00, 3.36it/s] 86%|████████▌ | 12/14 [00:03<00:00, 3.36it/s] 93%|█████████▎| 13/14 [00:03<00:00, 3.36it/s] 100%|██████████| 14/14 [00:04<00:00, 3.36it/s] 100%|██████████| 14/14 [00:04<00:00, 3.33it/s]
Version Details
- Version ID
816c99673841b9448bc2539834c16d40e0315bbf92fef0317b57a226727409bb- Version Created
- December 4, 2023