arthuryeti/dwiss-qwen-2 🔢📝✓❓🖼️ → 🖼️

▶️ 50 runs 📅 Aug 2025 ⚙️ Cog 0.16.2

About

Example Output

Prompt:

"A cinematic close-up of an elderly man’s wrinkled hand wearing a DWISS wristwatch, gently touching the small of a woman’s back. The woman is dressed in an elegant evening gown with delicate fabric, her posture graceful and poised. Soft, warm lighting casts subtle shadows, highlighting the textures of the skin, the shimmer of the watch, and the folds of the dress. The background is softly blurred, evoking a timeless, intimate, and sophisticated atmosphere."

Output

Performance Metrics

54.89s Prediction Time

92.45s Total Time

All Input Parameters

{
  "prompt": "A cinematic close-up of an elderly man’s wrinkled hand wearing a DWISS wristwatch, gently touching the small of a woman’s back. The woman is dressed in an elegant evening gown with delicate fabric, her posture graceful and poised. Soft, warm lighting casts subtle shadows, highlighting the textures of the skin, the shimmer of the watch, and the folds of the dress. The background is softly blurred, evoking a timeless, intimate, and sophisticated atmosphere.",
  "go_fast": false,
  "guidance": 4,
  "image_size": "optimize_for_quality",
  "lora_scale": 1,
  "aspect_ratio": "16:9",
  "output_format": "jpg",
  "enhance_prompt": false,
  "output_quality": 100,
  "negative_prompt": "",
  "num_inference_steps": 50
}

Input Parameters

seed Type: integer: Set a seed for reproducibility. Random by default.
width Type: integerRange: 512 - 2048: Custom width in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size).
height Type: integerRange: 512 - 2048: Custom height in pixels. Provide both width and height for custom dimensions (overrides aspect_ratio/image_size).
prompt (required) Type: string: The main prompt for image generation
go_fast Type: booleanDefault: false: Use LCM-LoRA to accelerate image generation (trades quality for 8x speed)
guidance Type: numberDefault: 4Range: 0 - 10: Guidance scale for image generation. Defaults to 1 if go_fast, else 3.5.
image_size Default: optimize_for_quality: Image size preset (quality = larger, speed = faster). Ignored if width and height are both provided.
lora_scale Type: numberDefault: 1Range: 0 - 3: Scale for LoRA weights (0 = base model, 1 = full LoRA)
aspect_ratio Default: 16:9: Aspect ratio for the generated image. Ignored if width and height are both provided.
output_format Default: webp: Format of the output images
enhance_prompt Type: booleanDefault: false: Automatically enhance the prompt for better image generation
output_quality Type: integerDefault: 80Range: 0 - 100: Quality when saving images (0-100, higher is better, 100 = lossless)
negative_prompt Type: stringDefault:: Things you do not want to see in your image
replicate_weights Type: string: Path to LoRA weights file. Leave blank to use base model.
num_inference_steps Type: integerDefault: 50Range: 0 - 50: Number of denoising steps. More steps = higher quality. Defaults to 4 if go_fast, else 28.

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

📐 Using quality preset for 16:9: 1664x928
Missing keys: []
LoRA loaded: dim=64, alpha=64, scale=1.0
Using random seed: 2073874652
Generating: A cinematic close-up of an elderly man’s wrinkled hand wearing a DWISS wristwatch, gently touching the small of a woman’s back. The woman is dressed in an elegant evening gown with delicate fabric, her posture graceful and poised. Soft, warm lighting casts subtle shadows, highlighting the textures of the skin, the shimmer of the watch, and the folds of the dress. The background is softly blurred, evoking a timeless, intimate, and sophisticated atmosphere. (1664x928, steps=50, seed=2073874652)
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:39,  1.23it/s]
  4%|▍         | 2/50 [00:01<00:38,  1.24it/s]
  6%|▌         | 3/50 [00:02<00:37,  1.24it/s]
  8%|▊         | 4/50 [00:03<00:36,  1.25it/s]
 10%|█         | 5/50 [00:04<00:36,  1.25it/s]
 12%|█▏        | 6/50 [00:04<00:35,  1.25it/s]
 14%|█▍        | 7/50 [00:05<00:34,  1.25it/s]
 16%|█▌        | 8/50 [00:06<00:33,  1.25it/s]
 18%|█▊        | 9/50 [00:07<00:32,  1.25it/s]
 20%|██        | 10/50 [00:08<00:32,  1.25it/s]
 22%|██▏       | 11/50 [00:08<00:31,  1.25it/s]
 24%|██▍       | 12/50 [00:09<00:30,  1.25it/s]
 26%|██▌       | 13/50 [00:10<00:29,  1.25it/s]
 28%|██▊       | 14/50 [00:11<00:28,  1.25it/s]
 30%|███       | 15/50 [00:12<00:28,  1.25it/s]
 32%|███▏      | 16/50 [00:12<00:27,  1.25it/s]
 34%|███▍      | 17/50 [00:13<00:26,  1.25it/s]
 36%|███▌      | 18/50 [00:14<00:25,  1.25it/s]
 38%|███▊      | 19/50 [00:15<00:24,  1.25it/s]
 40%|████      | 20/50 [00:16<00:24,  1.25it/s]
 42%|████▏     | 21/50 [00:16<00:23,  1.25it/s]
 44%|████▍     | 22/50 [00:17<00:22,  1.25it/s]
 46%|████▌     | 23/50 [00:18<00:21,  1.25it/s]
 48%|████▊     | 24/50 [00:19<00:20,  1.25it/s]
 50%|█████     | 25/50 [00:20<00:20,  1.25it/s]
 52%|█████▏    | 26/50 [00:20<00:19,  1.25it/s]
 54%|█████▍    | 27/50 [00:21<00:18,  1.25it/s]
 56%|█████▌    | 28/50 [00:22<00:17,  1.25it/s]
 58%|█████▊    | 29/50 [00:23<00:16,  1.25it/s]
 60%|██████    | 30/50 [00:24<00:16,  1.25it/s]
 62%|██████▏   | 31/50 [00:24<00:15,  1.25it/s]
 64%|██████▍   | 32/50 [00:25<00:14,  1.25it/s]
 66%|██████▌   | 33/50 [00:26<00:13,  1.25it/s]
 68%|██████▊   | 34/50 [00:27<00:12,  1.25it/s]
 70%|███████   | 35/50 [00:28<00:12,  1.25it/s]
 72%|███████▏  | 36/50 [00:28<00:11,  1.25it/s]
 74%|███████▍  | 37/50 [00:29<00:10,  1.25it/s]
 76%|███████▌  | 38/50 [00:30<00:09,  1.25it/s]
 78%|███████▊  | 39/50 [00:31<00:08,  1.25it/s]
 80%|████████  | 40/50 [00:32<00:08,  1.25it/s]
 82%|████████▏ | 41/50 [00:32<00:07,  1.25it/s]
 84%|████████▍ | 42/50 [00:33<00:06,  1.25it/s]
 86%|████████▌ | 43/50 [00:34<00:05,  1.25it/s]
 88%|████████▊ | 44/50 [00:35<00:04,  1.25it/s]
 90%|█████████ | 45/50 [00:36<00:04,  1.25it/s]
 92%|█████████▏| 46/50 [00:36<00:03,  1.25it/s]
 94%|█████████▍| 47/50 [00:37<00:02,  1.25it/s]
 96%|█████████▌| 48/50 [00:38<00:01,  1.25it/s]
 98%|█████████▊| 49/50 [00:39<00:00,  1.25it/s]
100%|██████████| 50/50 [00:40<00:00,  1.25it/s]
100%|██████████| 50/50 [00:40<00:00,  1.25it/s]
Generation took 40.30 seconds
Total safe images: 1/1

Version Details

Version ID: 674ea58f6bb3b22ac1ef8d3a14f660c2ec711e467bc7c0f891dd955385653c14
Version Created: August 20, 2025

Run on Replicate →