wasy89/kei_thumb 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"Ultra-realistic cinematic thumbnail, Keiber, a confident young man with short brown hair, light skin, and trimmed beard, wearing a plain long-sleeve brown sweater, standing against a futuristic blue-to-purple gradient background with subtle network pattern, large glowing blockchain domain name "keiber.web3" in bold yellow centered, Keiber holding a rectangular card with the same domain name in his left hand and pointing to it with his right hand, blue glowing open padlock icon with broken chain links on the left side, official Unstoppable Domains logo in the top right corner, professional studio lighting, realistic skin texture, soft shadows, highly detailed, cinematic color grading, 8k resolution"
Output
Performance Metrics
35.29s
Prediction Time
35.32s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "Ultra-realistic cinematic thumbnail, Keiber, a confident young man with short brown hair, light skin, and trimmed beard, wearing a plain long-sleeve brown sweater, standing against a futuristic blue-to-purple gradient background with subtle network pattern, large glowing blockchain domain name \"keiber.web3\" in bold yellow centered, Keiber holding a rectangular card with the same domain name in his left hand and pointing to it with his right hand, blue glowing open padlock icon with broken chain links on the left side, official Unstoppable Domains logo in the top right corner, professional studio lighting, realistic skin texture, soft shadows, highly detailed, cinematic color grading, 8k resolution\n",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 4,
"aspect_ratio": "16:9",
"output_format": "webp",
"guidance_scale": 8,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 35
}
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
Loaded LoRAs in 1.05s Using seed: 54403 Prompt: Ultra-realistic cinematic thumbnail, Keiber, a confident young man with short brown hair, light skin, and trimmed beard, wearing a plain long-sleeve brown sweater, standing against a futuristic blue-to-purple gradient background with subtle network pattern, large glowing blockchain domain name "keiber.web3" in bold yellow centered, Keiber holding a rectangular card with the same domain name in his left hand and pointing to it with his right hand, blue glowing open padlock icon with broken chain links on the left side, official Unstoppable Domains logo in the top right corner, professional studio lighting, realistic skin texture, soft shadows, highly detailed, cinematic color grading, 8k resolution [!] txt2img mode 0%| | 0/35 [00:00<?, ?it/s] 3%|▎ | 1/35 [00:00<00:32, 1.05it/s] 6%|▌ | 2/35 [00:01<00:27, 1.19it/s] 9%|▊ | 3/35 [00:02<00:28, 1.12it/s] 11%|█▏ | 4/35 [00:03<00:28, 1.09it/s] 14%|█▍ | 5/35 [00:04<00:27, 1.07it/s] 17%|█▋ | 6/35 [00:05<00:27, 1.06it/s] 20%|██ | 7/35 [00:06<00:26, 1.06it/s] 23%|██▎ | 8/35 [00:07<00:25, 1.06it/s] 26%|██▌ | 9/35 [00:08<00:24, 1.05it/s] 29%|██▊ | 10/35 [00:09<00:23, 1.05it/s] 31%|███▏ | 11/35 [00:10<00:22, 1.05it/s] 34%|███▍ | 12/35 [00:11<00:21, 1.05it/s] 37%|███▋ | 13/35 [00:12<00:20, 1.05it/s] 40%|████ | 14/35 [00:13<00:20, 1.05it/s] 43%|████▎ | 15/35 [00:14<00:19, 1.05it/s] 46%|████▌ | 16/35 [00:15<00:18, 1.05it/s] 49%|████▊ | 17/35 [00:16<00:17, 1.05it/s] 51%|█████▏ | 18/35 [00:16<00:16, 1.05it/s] 54%|█████▍ | 19/35 [00:17<00:15, 1.05it/s] 57%|█████▋ | 20/35 [00:18<00:14, 1.05it/s] 60%|██████ | 21/35 [00:19<00:13, 1.05it/s] 63%|██████▎ | 22/35 [00:20<00:12, 1.05it/s] 66%|██████▌ | 23/35 [00:21<00:11, 1.05it/s] 69%|██████▊ | 24/35 [00:22<00:10, 1.04it/s] 71%|███████▏ | 25/35 [00:23<00:09, 1.04it/s] 74%|███████▍ | 26/35 [00:24<00:08, 1.04it/s] 77%|███████▋ | 27/35 [00:25<00:07, 1.04it/s] 80%|████████ | 28/35 [00:26<00:06, 1.04it/s] 83%|████████▎ | 29/35 [00:27<00:05, 1.04it/s] 86%|████████▌ | 30/35 [00:28<00:04, 1.04it/s] 89%|████████▊ | 31/35 [00:29<00:03, 1.04it/s] 91%|█████████▏| 32/35 [00:30<00:02, 1.04it/s] 94%|█████████▍| 33/35 [00:31<00:01, 1.04it/s] 97%|█████████▋| 34/35 [00:32<00:00, 1.04it/s] 100%|██████████| 35/35 [00:33<00:00, 1.04it/s] 100%|██████████| 35/35 [00:33<00:00, 1.05it/s] Total safe images: 4 out of 4
Version Details
- Version ID
c2f4ce6635c6e803b2ced787acd9976968ce5c262a0500b4747da5c4f7083661- Version Created
- March 13, 2025