lucataco/ssd-lora-inference 🖼️🔢📝❓✓ → 🖼️

▶️ 2.7K runs 📅 Nov 2023 ⚙️ Cog 0.8.5 🔗 GitHub
image-inpainting image-to-image text-to-image

About

POC to run inference on SSD-1B LoRAs

Example Output

Prompt:

"A photo of TOK"

Output

Example output

Performance Metrics

14.34s Prediction Time
14.34s Total Time
All Input Parameters 
{
  "seed": 37543,
  "width": 1024,
  "height": 1024,
  "prompt": "A photo of TOK",
  "refine": "no_refiner",
  "lora_url": "https://replicate.delivery/pbxt/u5hevTlT560fI0D1TYxwozJk3gEJHAjVCubvbzngsaeoIIqjA/trained_model.tar",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": true,
  "high_noise_frac": 0.8,
  "negative_prompt": "",
  "prompt_strength": 0.8,
  "num_inference_steps": 25
}
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: A photo of TOK
Input prompt
lora_url (required) Type: string
Load Lora model
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.
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.
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
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
Output Schema

Output

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

Example Execution Logs 
LORA
Loading ssd txt2img pipeline...
Loading pipeline components...:   0%|          | 0/7 [00:00<?, ?it/s]
Loading pipeline components...:  14%|█▍        | 1/7 [00:00<00:01,  3.64it/s]
Loading pipeline components...:  57%|█████▋    | 4/7 [00:00<00:00,  8.12it/s]
Loading pipeline components...:  71%|███████▏  | 5/7 [00:00<00:00,  6.07it/s]
Loading pipeline components...: 100%|██████████| 7/7 [00:00<00:00,  8.21it/s]
Loading ssd lora weights...
Loading fine-tuned model
Does not have Unet. Assume we are using LoRA
Loading Unet LoRA
Using seed: 37543
Prompt: A photo of <s0><s1>
txt2img mode
  0%|          | 0/25 [00:00<?, ?it/s]
  4%|▍         | 1/25 [00:00<00:04,  5.95it/s]
  8%|▊         | 2/25 [00:00<00:03,  5.98it/s]
 12%|█▏        | 3/25 [00:00<00:03,  6.00it/s]
 16%|█▌        | 4/25 [00:00<00:03,  5.99it/s]
 20%|██        | 5/25 [00:00<00:03,  5.98it/s]
 24%|██▍       | 6/25 [00:01<00:03,  5.99it/s]
 28%|██▊       | 7/25 [00:01<00:02,  6.00it/s]
 32%|███▏      | 8/25 [00:01<00:02,  6.01it/s]
 36%|███▌      | 9/25 [00:01<00:02,  6.02it/s]
 40%|████      | 10/25 [00:01<00:02,  6.02it/s]
 44%|████▍     | 11/25 [00:01<00:02,  6.02it/s]
 48%|████▊     | 12/25 [00:01<00:02,  6.02it/s]
 52%|█████▏    | 13/25 [00:02<00:01,  6.02it/s]
 56%|█████▌    | 14/25 [00:02<00:01,  6.02it/s]
 60%|██████    | 15/25 [00:02<00:01,  6.02it/s]
 64%|██████▍   | 16/25 [00:02<00:01,  6.03it/s]
 68%|██████▊   | 17/25 [00:02<00:01,  6.03it/s]
 72%|███████▏  | 18/25 [00:02<00:01,  6.02it/s]
 76%|███████▌  | 19/25 [00:03<00:00,  6.02it/s]
 80%|████████  | 20/25 [00:03<00:00,  6.02it/s]
 84%|████████▍ | 21/25 [00:03<00:00,  6.02it/s]
 88%|████████▊ | 22/25 [00:03<00:00,  6.02it/s]
 92%|█████████▏| 23/25 [00:03<00:00,  6.01it/s]
 96%|█████████▌| 24/25 [00:03<00:00,  6.00it/s]
100%|██████████| 25/25 [00:04<00:00,  6.01it/s]
100%|██████████| 25/25 [00:04<00:00,  6.01it/s]
Version Details
Version ID
c12da324765b82d631da86b55b22d50e3533f49caa616f029517a0af328be570
Version Created
November 8, 2023
Run on Replicate →