fofr/sdxl-sonic-2 🖼️🔢📝❓✓ → 🖼️

▶️ 2.4K runs 📅 Aug 2023 ⚙️ Cog 0.8.5
game-asset-generation image-to-image pixel-art text-to-image

About

Example Output

Prompt:

"A screenshot in the style of TOK, pixel art, 2d platform game, sharp, snowy mountain scene"

Output

Example outputExample outputExample outputExample output

Performance Metrics

61.49s Prediction Time
61.47s Total Time
All Input Parameters
{
  "width": 1536,
  "height": 768,
  "prompt": "A screenshot in the style of TOK, pixel art, 2d platform game, sharp, snowy mountain scene",
  "refine": "expert_ensemble_refiner",
  "scheduler": "K_EULER",
  "lora_scale": 0.6,
  "num_outputs": 4,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.95,
  "negative_prompt": "soft, blurry",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}
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: DDIM
scheduler
lora_scale Type: numberDefault: 0.6Range: 0 - 1
LoRA additive scale.
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
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 2561
Prompt: A screenshot in the style of <s0><s1>, pixel art, 2d platform game, sharp, snowy mountain scene
txt2img mode
  0%|          | 0/47 [00:00<?, ?it/s]
  2%|▏         | 1/47 [00:01<00:52,  1.15s/it]
  4%|▍         | 2/47 [00:02<00:51,  1.15s/it]
  6%|▋         | 3/47 [00:03<00:50,  1.15s/it]
  9%|▊         | 4/47 [00:04<00:49,  1.15s/it]
 11%|█         | 5/47 [00:05<00:48,  1.15s/it]
 13%|█▎        | 6/47 [00:06<00:47,  1.15s/it]
 15%|█▍        | 7/47 [00:08<00:46,  1.15s/it]
 17%|█▋        | 8/47 [00:09<00:45,  1.15s/it]
 19%|█▉        | 9/47 [00:10<00:43,  1.15s/it]
 21%|██▏       | 10/47 [00:11<00:42,  1.15s/it]
 23%|██▎       | 11/47 [00:12<00:41,  1.16s/it]
 26%|██▌       | 12/47 [00:13<00:40,  1.16s/it]
 28%|██▊       | 13/47 [00:15<00:39,  1.16s/it]
 30%|██▉       | 14/47 [00:16<00:38,  1.16s/it]
 32%|███▏      | 15/47 [00:17<00:36,  1.16s/it]
 34%|███▍      | 16/47 [00:18<00:35,  1.16s/it]
 36%|███▌      | 17/47 [00:19<00:34,  1.16s/it]
 38%|███▊      | 18/47 [00:20<00:33,  1.16s/it]
 40%|████      | 19/47 [00:21<00:32,  1.16s/it]
 43%|████▎     | 20/47 [00:23<00:31,  1.16s/it]
 45%|████▍     | 21/47 [00:24<00:30,  1.16s/it]
 47%|████▋     | 22/47 [00:25<00:28,  1.16s/it]
 49%|████▉     | 23/47 [00:26<00:27,  1.16s/it]
 51%|█████     | 24/47 [00:27<00:26,  1.16s/it]
 53%|█████▎    | 25/47 [00:28<00:25,  1.16s/it]
 55%|█████▌    | 26/47 [00:30<00:24,  1.16s/it]
 57%|█████▋    | 27/47 [00:31<00:23,  1.16s/it]
 60%|█████▉    | 28/47 [00:32<00:21,  1.16s/it]
 62%|██████▏   | 29/47 [00:33<00:20,  1.16s/it]
 64%|██████▍   | 30/47 [00:34<00:19,  1.16s/it]
 66%|██████▌   | 31/47 [00:35<00:18,  1.16s/it]
 68%|██████▊   | 32/47 [00:36<00:17,  1.16s/it]
 70%|███████   | 33/47 [00:38<00:16,  1.16s/it]
 72%|███████▏  | 34/47 [00:39<00:15,  1.16s/it]
 74%|███████▍  | 35/47 [00:40<00:13,  1.16s/it]
 77%|███████▋  | 36/47 [00:41<00:12,  1.16s/it]
 79%|███████▊  | 37/47 [00:42<00:11,  1.16s/it]
 81%|████████  | 38/47 [00:43<00:10,  1.16s/it]
 83%|████████▎ | 39/47 [00:45<00:09,  1.16s/it]
 85%|████████▌ | 40/47 [00:46<00:08,  1.16s/it]
 87%|████████▋ | 41/47 [00:47<00:06,  1.16s/it]
 89%|████████▉ | 42/47 [00:48<00:05,  1.16s/it]
 91%|█████████▏| 43/47 [00:49<00:04,  1.16s/it]
 94%|█████████▎| 44/47 [00:50<00:03,  1.16s/it]
 96%|█████████▌| 45/47 [00:52<00:02,  1.16s/it]
 98%|█████████▊| 46/47 [00:53<00:01,  1.16s/it]
100%|██████████| 47/47 [00:54<00:00,  1.16s/it]
100%|██████████| 47/47 [00:54<00:00,  1.16s/it]
  0%|          | 0/3 [00:00<?, ?it/s]
 33%|███▎      | 1/3 [00:00<00:01,  1.06it/s]
 67%|██████▋   | 2/3 [00:01<00:00,  1.06it/s]
100%|██████████| 3/3 [00:02<00:00,  1.06it/s]
100%|██████████| 3/3 [00:02<00:00,  1.06it/s]
Version Details
Version ID
d9b22cdf778d4ccaf2b6a84a06a2eaa754305703d46983e1a996fe1eabbfd26c
Version Created
August 8, 2023
Run on Replicate →