pellmellism/xkcd 🖼️🔢❓📝✓ → 🖼️
About
epic xkcd comics
Example Output
Prompt:
"A black and white stick figure comic panel in XKCD style. framed low on the ground looking up to see a stick figure looking at a comically oversized rocket blasting off to the moon. The linework should be simple and clean, typical of XKCD comics."
Output



Performance Metrics
63.93s
Prediction Time
109.91s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "A black and white stick figure comic panel in XKCD style. framed low on the ground looking up to see a stick figure looking at a comically oversized rocket blasting off to the moon. The linework should be simple and clean, typical of XKCD comics.",
"lora_scale": 0.7,
"num_outputs": 4,
"aspect_ratio": "16:9",
"output_format": "png",
"guidance_scale": 5,
"output_quality": 80,
"num_inference_steps": 50
}
Input Parameters
- mask
- Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- seed
- Random seed. Set for reproducible generation
- image
- Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- model
- Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
- width
- Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
- height
- Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
- prompt (required)
- Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
- go_fast
- Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
- extra_lora
- Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
- lora_scale
- Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
- megapixels
- Approximate number of megapixels for generated image
- num_outputs
- Number of outputs to generate
- aspect_ratio
- Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
- output_format
- Format of the output images
- guidance_scale
- Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
- output_quality
- Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
- prompt_strength
- Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
- extra_lora_scale
- Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
- replicate_weights
- Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
- num_inference_steps
- Number of denoising steps. More steps can give more detailed images, but take longer.
- disable_safety_checker
- Disable safety checker for generated images.
Output Schema
Output
Example Execution Logs
Using seed: 26369 Prompt: A black and white stick figure comic panel in XKCD style. framed low on the ground looking up to see a stick figure looking at a comically oversized rocket blasting off to the moon. The linework should be simple and clean, typical of XKCD comics. txt2img mode Using dev model Loading LoRA weights Ensuring enough disk space... Free disk space: 9402024132608 Downloading weights 2024-08-20T02:58:21Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/76c2d9e6a1e943a3 url=https://replicate.delivery/yhqm/BaP7ucoCH47PEZzjbEZAwd1hfD1QtXTfomzKCMFLlpyDKbUTA/trained_model.tar 2024-08-20T02:58:26Z | INFO | [ Complete ] dest=/src/weights-cache/76c2d9e6a1e943a3 size="174 MB" total_elapsed=4.342s url=https://replicate.delivery/yhqm/BaP7ucoCH47PEZzjbEZAwd1hfD1QtXTfomzKCMFLlpyDKbUTA/trained_model.tar b'' Downloaded weights in 4.376370668411255 seconds LoRA weights loaded successfully 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:48, 1.02it/s] 4%|▍ | 2/50 [00:01<00:41, 1.15it/s] 6%|▌ | 3/50 [00:02<00:43, 1.08it/s] 8%|▊ | 4/50 [00:03<00:43, 1.05it/s] 10%|█ | 5/50 [00:04<00:43, 1.04it/s] 12%|█▏ | 6/50 [00:05<00:42, 1.03it/s] 14%|█▍ | 7/50 [00:06<00:42, 1.02it/s] 16%|█▌ | 8/50 [00:07<00:41, 1.02it/s] 18%|█▊ | 9/50 [00:08<00:40, 1.02it/s] 20%|██ | 10/50 [00:09<00:39, 1.02it/s] 22%|██▏ | 11/50 [00:10<00:38, 1.01it/s] 24%|██▍ | 12/50 [00:11<00:37, 1.01it/s] 26%|██▌ | 13/50 [00:12<00:36, 1.01it/s] 28%|██▊ | 14/50 [00:13<00:35, 1.01it/s] 30%|███ | 15/50 [00:14<00:34, 1.01it/s] 32%|███▏ | 16/50 [00:15<00:33, 1.01it/s] 34%|███▍ | 17/50 [00:16<00:32, 1.01it/s] 36%|███▌ | 18/50 [00:17<00:31, 1.01it/s] 38%|███▊ | 19/50 [00:18<00:30, 1.01it/s] 40%|████ | 20/50 [00:19<00:29, 1.01it/s] 42%|████▏ | 21/50 [00:20<00:28, 1.01it/s] 44%|████▍ | 22/50 [00:21<00:27, 1.01it/s] 46%|████▌ | 23/50 [00:22<00:26, 1.01it/s] 48%|████▊ | 24/50 [00:23<00:25, 1.01it/s] 50%|█████ | 25/50 [00:24<00:24, 1.01it/s] 52%|█████▏ | 26/50 [00:25<00:23, 1.01it/s] 54%|█████▍ | 27/50 [00:26<00:22, 1.01it/s] 56%|█████▌ | 28/50 [00:27<00:21, 1.01it/s] 58%|█████▊ | 29/50 [00:28<00:20, 1.01it/s] 60%|██████ | 30/50 [00:29<00:19, 1.01it/s] 62%|██████▏ | 31/50 [00:30<00:18, 1.01it/s] 64%|██████▍ | 32/50 [00:31<00:17, 1.01it/s] 66%|██████▌ | 33/50 [00:32<00:16, 1.01it/s] 68%|██████▊ | 34/50 [00:33<00:15, 1.01it/s] 70%|███████ | 35/50 [00:34<00:14, 1.01it/s] 72%|███████▏ | 36/50 [00:35<00:13, 1.01it/s] 74%|███████▍ | 37/50 [00:36<00:12, 1.01it/s] 76%|███████▌ | 38/50 [00:37<00:11, 1.01it/s] 78%|███████▊ | 39/50 [00:38<00:10, 1.01it/s] 80%|████████ | 40/50 [00:39<00:09, 1.01it/s] 82%|████████▏ | 41/50 [00:40<00:08, 1.01it/s] 84%|████████▍ | 42/50 [00:41<00:07, 1.01it/s] 86%|████████▌ | 43/50 [00:42<00:06, 1.01it/s] 88%|████████▊ | 44/50 [00:43<00:05, 1.01it/s] 90%|█████████ | 45/50 [00:44<00:04, 1.01it/s] 92%|█████████▏| 46/50 [00:45<00:03, 1.01it/s] 94%|█████████▍| 47/50 [00:46<00:02, 1.01it/s] 96%|█████████▌| 48/50 [00:47<00:01, 1.01it/s] 98%|█████████▊| 49/50 [00:48<00:00, 1.01it/s] 100%|██████████| 50/50 [00:49<00:00, 1.01it/s] 100%|██████████| 50/50 [00:49<00:00, 1.01it/s]
Version Details
- Version ID
7e0502efc2a94a6b42f8572bade751196af37e9f4c4e430cd3d5c19c1ed31647- Version Created
- August 20, 2024