aliadhami/3d-sheet 🖼️🔢❓📝✓ → 🖼️
About
Generates minimal, consistent 3-view design for objects in the style of technical 3D reference sheets. Outputs include front, back, and side views with consistent proportions against a white background.
Example Output
Prompt:
"In the style of 3dsheet, three consistent views of the same realistic Jesus head-and-neck figure with crown of thorns, lifelike skin, brown hair, greenish eyes, texture, visible neck, and upper shoulders. Front view shows a solemn face with natural facial features, detailed beard, crown resting on the brow, and fabric line of a robe at the shoulders. Back view displays textured hair flowing down the neck, crown wrapping fully around the head with thorn detail, and subtle shoulder form. Side view presents the realistic facial profile, visible skin folds on the neck, sharp crown thorns, and robe edge at the upper shoulder. All three views maintain consistent proportions of this single realistic Jesus head-and-neck figure against a white background."
Output
Performance Metrics
26.05s
Prediction Time
55.14s
Total Time
All Input Parameters
{
"model": "dev",
"width": 1440,
"height": 593,
"prompt": "In the style of 3dsheet, three consistent views of the same realistic Jesus head-and-neck figure with crown of thorns, lifelike skin, brown hair, greenish eyes, texture, visible neck, and upper shoulders. Front view shows a solemn face with natural facial features, detailed beard, crown resting on the brow, and fabric line of a robe at the shoulders. Back view displays textured hair flowing down the neck, crown wrapping fully around the head with thorn detail, and subtle shoulder form. Side view presents the realistic facial profile, visible skin folds on the neck, sharp crown thorns, and robe edge at the upper shoulder. All three views maintain consistent proportions of this single realistic Jesus head-and-neck figure against a white background.",
"go_fast": false,
"lora_scale": 0.7,
"megapixels": "1",
"num_outputs": 4,
"aspect_ratio": "custom",
"output_format": "webp",
"guidance_scale": 3,
"output_quality": 80,
"prompt_strength": 0.79,
"extra_lora_scale": 2.63,
"num_inference_steps": 28
}
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 0.57s Using seed: 17291 Prompt: In the style of 3dsheet, three consistent views of the same realistic Jesus head-and-neck figure with crown of thorns, lifelike skin, brown hair, greenish eyes, texture, visible neck, and upper shoulders. Front view shows a solemn face with natural facial features, detailed beard, crown resting on the brow, and fabric line of a robe at the shoulders. Back view displays textured hair flowing down the neck, crown wrapping fully around the head with thorn detail, and subtle shoulder form. Side view presents the realistic facial profile, visible skin folds on the neck, sharp crown thorns, and robe edge at the upper shoulder. All three views maintain consistent proportions of this single realistic Jesus head-and-neck figure against a white background. [!] txt2img mode 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:21, 1.23it/s] 7%|▋ | 2/28 [00:01<00:19, 1.37it/s] 11%|█ | 3/28 [00:02<00:19, 1.30it/s] 14%|█▍ | 4/28 [00:03<00:18, 1.27it/s] 18%|█▊ | 5/28 [00:03<00:18, 1.26it/s] 21%|██▏ | 6/28 [00:04<00:17, 1.24it/s] 25%|██▌ | 7/28 [00:05<00:16, 1.24it/s] 29%|██▊ | 8/28 [00:06<00:16, 1.24it/s] 32%|███▏ | 9/28 [00:07<00:15, 1.23it/s] 36%|███▌ | 10/28 [00:08<00:14, 1.23it/s] 39%|███▉ | 11/28 [00:08<00:13, 1.23it/s] 43%|████▎ | 12/28 [00:09<00:13, 1.23it/s] 46%|████▋ | 13/28 [00:10<00:12, 1.23it/s] 50%|█████ | 14/28 [00:11<00:11, 1.23it/s] 54%|█████▎ | 15/28 [00:12<00:10, 1.23it/s] 57%|█████▋ | 16/28 [00:12<00:09, 1.23it/s] 61%|██████ | 17/28 [00:13<00:08, 1.23it/s] 64%|██████▍ | 18/28 [00:14<00:08, 1.23it/s] 68%|██████▊ | 19/28 [00:15<00:07, 1.23it/s] 71%|███████▏ | 20/28 [00:16<00:06, 1.23it/s] 75%|███████▌ | 21/28 [00:16<00:05, 1.23it/s] 79%|███████▊ | 22/28 [00:17<00:04, 1.23it/s] 82%|████████▏ | 23/28 [00:18<00:04, 1.23it/s] 86%|████████▌ | 24/28 [00:19<00:03, 1.23it/s] 89%|████████▉ | 25/28 [00:20<00:02, 1.23it/s] 93%|█████████▎| 26/28 [00:21<00:01, 1.23it/s] 96%|█████████▋| 27/28 [00:21<00:00, 1.23it/s] 100%|██████████| 28/28 [00:22<00:00, 1.23it/s] 100%|██████████| 28/28 [00:22<00:00, 1.24it/s] Total safe images: 4 out of 4
Version Details
- Version ID
7edfa9773387328f8d75a447a345b0b14a47278d579b25d4f640bf57caeb0891- Version Created
- March 27, 2025