majusculeqc/distordius 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
Photorealistic image, 8K resolution, ultra-detailed, depicting a film set, indoors, with a slightly smoky atmosphere.
In the midground, MAJUSCULE, the film director stands facing the camera directly. MAJUSCULE is highly detailed and clearly visible. The film director expression is serious and focused.
In the foreground, out of focus, the back of a large, professional film camera mounted on a sturdy tripod is visible. The camera is pointed directly at MAJUSCULE. Shallow depth of field, focus on lights.
The background is dark and mostly out of focus, but reveals various film equipment, such as lighting rigs, softboxes, c-stands, cables, and other gear, scattered around the set, adding to the authentic film set environment.
The scene is illuminated with a strong, directional, cool blue light source coming from the top right of the frame. A secondary, softer, warmer light source illuminates the left side of the scene. Emphasis on realistic reflections, highlights, and shadows, particularly on the film director and the metallic parts of the camera.
Lens: 35mm, Aperture: f/2.8, ISO: 800, Shutter speed: 1/60 sec., Shot with a Canon EOS 5D Mark IV. Ray tracing, global illumination.
"Output
Performance Metrics
8.31s
Prediction Time
8.34s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "Photorealistic image, 8K resolution, ultra-detailed, depicting a film set, indoors, with a slightly smoky atmosphere.\n\nIn the midground, MAJUSCULE, the film director stands facing the camera directly. MAJUSCULE is highly detailed and clearly visible. The film director expression is serious and focused.\n\nIn the foreground, out of focus, the back of a large, professional film camera mounted on a sturdy tripod is visible. The camera is pointed directly at MAJUSCULE. Shallow depth of field, focus on lights.\n\nThe background is dark and mostly out of focus, but reveals various film equipment, such as lighting rigs, softboxes, c-stands, cables, and other gear, scattered around the set, adding to the authentic film set environment.\n\nThe scene is illuminated with a strong, directional, cool blue light source coming from the top right of the frame. A secondary, softer, warmer light source illuminates the left side of the scene. Emphasis on realistic reflections, highlights, and shadows, particularly on the film director and the metallic parts of the camera.\n\nLens: 35mm, Aperture: f/2.8, ISO: 800, Shutter speed: 1/60 sec., Shot with a Canon EOS 5D Mark IV. Ray tracing, global illumination.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "16:9",
"output_format": "webp",
"guidance_scale": 3,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"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
2025-01-09 14:36:47.743 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-09 14:36:47.744 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 92%|█████████▏| 280/304 [00:00<00:00, 2787.93it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2735.63it/s] 2025-01-09 14:36:47.855 | SUCCESS | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.11s free=29302770999296 Downloading weights 2025-01-09T14:36:47Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp9t22_rhu/weights url=https://replicate.delivery/xezq/C13PRPKffJoRvklpGjCfVHzCbOHbuw7LHZqZnRwAnjSqEnGoA/trained_model.tar 2025-01-09T14:36:49Z | INFO | [ Complete ] dest=/tmp/tmp9t22_rhu/weights size="172 MB" total_elapsed=1.925s url=https://replicate.delivery/xezq/C13PRPKffJoRvklpGjCfVHzCbOHbuw7LHZqZnRwAnjSqEnGoA/trained_model.tar Downloaded weights in 1.95s 2025-01-09 14:36:49.807 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/91223b5e137f0845 2025-01-09 14:36:49.878 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded 2025-01-09 14:36:49.878 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-09 14:36:49.878 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 92%|█████████▏| 280/304 [00:00<00:00, 2790.54it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2737.88it/s] 2025-01-09 14:36:49.990 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s Using seed: 65075 0it [00:00, ?it/s] 1it [00:00, 8.46it/s] 2it [00:00, 5.89it/s] 3it [00:00, 5.37it/s] 4it [00:00, 5.16it/s] 5it [00:00, 5.04it/s] 6it [00:01, 4.95it/s] 7it [00:01, 4.92it/s] 8it [00:01, 4.90it/s] 9it [00:01, 4.89it/s] 10it [00:01, 4.88it/s] 11it [00:02, 4.86it/s] 12it [00:02, 4.85it/s] 13it [00:02, 4.84it/s] 14it [00:02, 4.85it/s] 15it [00:03, 4.85it/s] 16it [00:03, 4.84it/s] 17it [00:03, 4.83it/s] 18it [00:03, 4.83it/s] 19it [00:03, 4.83it/s] 20it [00:04, 4.83it/s] 21it [00:04, 4.83it/s] 22it [00:04, 4.83it/s] 23it [00:04, 4.82it/s] 24it [00:04, 4.83it/s] 25it [00:05, 4.82it/s] 26it [00:05, 4.82it/s] 27it [00:05, 4.83it/s] 28it [00:05, 4.83it/s] 28it [00:05, 4.91it/s] Total safe images: 1 out of 1
Version Details
- Version ID
fc331a5423353358d8386846fae45e61f2395112d90f0de580a5cf4d2ff7e087- Version Created
- January 9, 2025