fermatresearch/photorealistic-fx-lora 🔢🖼️❓📝 → 🖼️

▶️ 5.2K runs 📅 Jun 2023 ⚙️ Cog 0.7.2

About

Photorealistic FX by RunDiffusion with LoRA integrated. Works as good or better than RealisticVision.

Example Output

Prompt:

"Product image of a gaming mouse in the style of <1>, colorful"

Output

Performance Metrics

5.87s Prediction Time

5.82s Total Time

All Input Parameters

{
  "width": "768",
  "height": "768",
  "prompt": "Product image of a gaming mouse in the style of <1>, colorful",
  "lora_urls": "https://replicate.delivery/pbxt/ecXsN8aT9WUYFS4UTObSpCNjzVvUm3WC3wf9kphbxlCeejnCB/tmpt5g5pb26sketchzip.safetensors",
  "scheduler": "DPMSolverMultistep",
  "lora_scales": "0.5",
  "num_outputs": 1,
  "adapter_type": "sketch",
  "guidance_scale": 3.5,
  "negative_prompt": "ugly, not professional, amateur, bad quality",
  "prompt_strength": 0.8,
  "num_inference_steps": 35
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
image Type: string: (Img2Img) Inital image to generate variations of. If this is not none, Img2Img will be invoked.
width Default: 512: Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
height Default: 512: Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
prompt Type: stringDefault: a photo of <1> riding a horse on mars: Input prompt. Use <1>, <2>, <3>, etc., to specify LoRA concepts
lora_urls Type: stringDefault:: List of urls for safetensors of lora models, seperated with | .
scheduler Default: DPMSolverMultistep: Choose a scheduler.
lora_scales Type: stringDefault: 0.5: List of scales for safetensors of lora models, seperated with |
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output.
adapter_type Default: sketch: (T2I-adapter) Choose an adapter type for the additional condition.
guidance_scale Type: numberDefault: 7.5Range: 1 - 20: Scale for classifier-free guidance
negative_prompt Type: stringDefault:: Specify things to not see in the output
prompt_strength Type: numberDefault: 0.8: (Img2Img) Prompt strength when providing the image. 1.0 corresponds to full destruction of information in init image
num_inference_steps Type: integerDefault: 35Range: 1 - 500: Number of denoising steps
adapter_condition_image Type: string: (T2I-adapter) Adapter Condition Image to gain extra control over generation. If this is not none, T2I adapter will be invoked. Width, Height of this image must match the above parameter, or dimension of the Img2Img image.

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Using seed: 27427
Generating image of 768 x 768 with prompt: Product image of a gaming mouse in the style of <1>, colorful
The requested LoRAs are loaded.
  0%|          | 0/35 [00:00<?, ?it/s]
  3%|▎         | 1/35 [00:00<00:04,  7.30it/s]
  6%|▌         | 2/35 [00:00<00:04,  7.30it/s]
  9%|▊         | 3/35 [00:00<00:04,  7.24it/s]
 11%|█▏        | 4/35 [00:00<00:04,  7.07it/s]
 14%|█▍        | 5/35 [00:00<00:04,  7.36it/s]
 17%|█▋        | 6/35 [00:00<00:03,  7.28it/s]
 20%|██        | 7/35 [00:00<00:03,  7.35it/s]
 23%|██▎       | 8/35 [00:01<00:03,  7.51it/s]
 26%|██▌       | 9/35 [00:01<00:03,  7.36it/s]
 29%|██▊       | 10/35 [00:01<00:03,  7.48it/s]
 31%|███▏      | 11/35 [00:01<00:03,  7.45it/s]
 34%|███▍      | 12/35 [00:01<00:03,  7.53it/s]
 37%|███▋      | 13/35 [00:01<00:02,  7.65it/s]
 40%|████      | 14/35 [00:01<00:02,  7.71it/s]
 43%|████▎     | 15/35 [00:02<00:02,  7.76it/s]
 46%|████▌     | 16/35 [00:02<00:02,  7.83it/s]
 49%|████▊     | 17/35 [00:02<00:02,  7.88it/s]
 51%|█████▏    | 18/35 [00:02<00:02,  7.66it/s]
 54%|█████▍    | 19/35 [00:02<00:02,  7.55it/s]
 57%|█████▋    | 20/35 [00:02<00:01,  7.55it/s]
 60%|██████    | 21/35 [00:02<00:01,  7.65it/s]
 63%|██████▎   | 22/35 [00:02<00:01,  7.77it/s]
 66%|██████▌   | 23/35 [00:03<00:01,  7.82it/s]
 69%|██████▊   | 24/35 [00:03<00:01,  7.86it/s]
 71%|███████▏  | 25/35 [00:03<00:01,  7.88it/s]
 74%|███████▍  | 26/35 [00:03<00:01,  7.92it/s]
 77%|███████▋  | 27/35 [00:03<00:01,  7.76it/s]
 80%|████████  | 28/35 [00:03<00:00,  7.76it/s]
 83%|████████▎ | 29/35 [00:03<00:00,  7.80it/s]
 86%|████████▌ | 30/35 [00:03<00:00,  7.84it/s]
 89%|████████▊ | 31/35 [00:04<00:00,  7.83it/s]
 91%|█████████▏| 32/35 [00:04<00:00,  7.82it/s]
 94%|█████████▍| 33/35 [00:04<00:00,  7.51it/s]
 97%|█████████▋| 34/35 [00:04<00:00,  7.38it/s]
100%|██████████| 35/35 [00:04<00:00,  7.32it/s]
100%|██████████| 35/35 [00:04<00:00,  7.59it/s]

Version Details

Version ID: 03aa3c93f5bbec7830d305ca8be29d52350f92f25e9d8e5793535cfb0c62a196
Version Created: June 14, 2023

Run on Replicate →