chuanzi/su7xiaomi 🖼️🔢📝❓✓ → 🖼️

▶️ 68 runs 📅 May 2024 ⚙️ Cog 0.8.6

About

小米 su7 lora测试

Example Output

Prompt:

"a purple su7 car in new york city street lot from above, wide shot, solo"

Output

Performance Metrics

12.34s Prediction Time

14.84s Total Time

All Input Parameters

{
  "width": 1024,
  "height": 1024,
  "prompt": "a purple su7 car in new york city street lot from above, wide shot, solo",
  "refine": "no_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.7,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry",
  "prompt_strength": 0.8,
  "num_inference_steps": 30
}

Input Parameters

mask Type: string: Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
seed Type: integer: Random seed. Leave blank to randomize the seed
image Type: string: Input image for img2img or inpaint mode
width Type: integerDefault: 1024: Width of output image
height Type: integerDefault: 1024: Height of output image
prompt Type: stringDefault: An astronaut riding a rainbow unicorn: Input prompt
refine Default: no_refiner: Which refine style to use
scheduler Default: K_EULER: scheduler
lora_scale Type: numberDefault: 0.6Range: 0 - 1: LoRA additive scale. Only applicable on trained models.
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output.
refine_steps Type: integer: For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
guidance_scale Type: numberDefault: 7.5Range: 1 - 50: Scale for classifier-free guidance
apply_watermark Type: booleanDefault: true: Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
high_noise_frac Type: numberDefault: 0.8Range: 0 - 1: For expert_ensemble_refiner, the fraction of noise to use
negative_prompt Type: stringDefault:: Input Negative Prompt
prompt_strength Type: numberDefault: 0.8Range: 0 - 1: Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
replicate_weights Type: string: Replicate LoRA weights to use. Leave blank to use the default weights.
num_inference_steps Type: integerDefault: 50Range: 1 - 500: Number of denoising steps
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Using seed: 23516
Ensuring enough disk space...
Free disk space: 2076042784768
Downloading weights: https://replicate.delivery/pbxt/d7LIEFnuDapRFpV63QW7znlbKSfh32tPLx6SefGzmrl0PMplA/trained_model.tar
2024-05-15T12:59:20Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/e862c3983114ce13 url=https://replicate.delivery/pbxt/d7LIEFnuDapRFpV63QW7znlbKSfh32tPLx6SefGzmrl0PMplA/trained_model.tar
2024-05-15T12:59:21Z | INFO  | [ Complete ] dest=/src/weights-cache/e862c3983114ce13 size="186 MB" total_elapsed=0.789s url=https://replicate.delivery/pbxt/d7LIEFnuDapRFpV63QW7znlbKSfh32tPLx6SefGzmrl0PMplA/trained_model.tar
b''
Downloaded weights in 0.970226526260376 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: a purple <s0><s1> car in new york city street lot from above, wide shot, solo
txt2img mode
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:07,  3.71it/s]
  7%|▋         | 2/30 [00:00<00:07,  3.71it/s]
 10%|█         | 3/30 [00:00<00:07,  3.71it/s]
 13%|█▎        | 4/30 [00:01<00:07,  3.70it/s]
 17%|█▋        | 5/30 [00:01<00:06,  3.70it/s]
 20%|██        | 6/30 [00:01<00:06,  3.70it/s]
 23%|██▎       | 7/30 [00:01<00:06,  3.70it/s]
 27%|██▋       | 8/30 [00:02<00:05,  3.70it/s]
 30%|███       | 9/30 [00:02<00:05,  3.70it/s]
 33%|███▎      | 10/30 [00:02<00:05,  3.70it/s]
 37%|███▋      | 11/30 [00:02<00:05,  3.70it/s]
 40%|████      | 12/30 [00:03<00:04,  3.70it/s]
 43%|████▎     | 13/30 [00:03<00:04,  3.69it/s]
 47%|████▋     | 14/30 [00:03<00:04,  3.70it/s]
 50%|█████     | 15/30 [00:04<00:04,  3.69it/s]
 53%|█████▎    | 16/30 [00:04<00:03,  3.69it/s]
 57%|█████▋    | 17/30 [00:04<00:03,  3.69it/s]
 60%|██████    | 18/30 [00:04<00:03,  3.69it/s]
 63%|██████▎   | 19/30 [00:05<00:02,  3.69it/s]
 67%|██████▋   | 20/30 [00:05<00:02,  3.69it/s]
 70%|███████   | 21/30 [00:05<00:02,  3.69it/s]
 73%|███████▎  | 22/30 [00:05<00:02,  3.69it/s]
 77%|███████▋  | 23/30 [00:06<00:01,  3.68it/s]
 80%|████████  | 24/30 [00:06<00:01,  3.68it/s]
 83%|████████▎ | 25/30 [00:06<00:01,  3.68it/s]
 87%|████████▋ | 26/30 [00:07<00:01,  3.68it/s]
 90%|█████████ | 27/30 [00:07<00:00,  3.68it/s]
 93%|█████████▎| 28/30 [00:07<00:00,  3.68it/s]
 97%|█████████▋| 29/30 [00:07<00:00,  3.68it/s]
100%|██████████| 30/30 [00:08<00:00,  3.68it/s]
100%|██████████| 30/30 [00:08<00:00,  3.69it/s]

Version Details

Version ID: ac26ec54c06329d6136b1c81a8d28166cd0350101b55084c57a359c97148e719
Version Created: May 15, 2024

Run on Replicate →