fofr/sd3-explorer 🔢❓📝✓ → 🖼️

▶️ 32.5K runs 📅 Jun 2024 ⚙️ Cog 0.9.7 🔗 GitHub 📄 Paper ⚖️ License
stable-diffusion-3 text-to-image

About

A model for experimenting with all the SD3 settings. Non-commercial use only, unless you have a Stability AI Self Hosted License.

Example Output

Prompt:

"a man and woman are standing together against a backdrop, the backdrop is divided equally in half down the middle, left side is red, right side is gold, the woman is wearing a t-shirt with a yoda motif, she has a long skirt with birds on it, the man is wearing a three piece purple suit, he has spiky blue hair"

Output

Example output

Performance Metrics

8.65s Prediction Time
8.68s Total Time
All Input Parameters
{
  "model": "sd3_medium_incl_clips_t5xxlfp16.safetensors",
  "shift": 3,
  "steps": 28,
  "width": 1024,
  "height": 1024,
  "prompt": "a man and woman are standing together against a backdrop, the backdrop is divided equally in half down the middle, left side is red, right side is gold, the woman is wearing a t-shirt with a yoda motif, she has a long skirt with birds on it, the man is wearing a three piece purple suit, he has spiky blue hair",
  "sampler": "dpmpp_2m",
  "scheduler": "sgm_uniform",
  "output_format": "webp",
  "guidance_scale": 4.5,
  "output_quality": 80,
  "negative_prompt": "",
  "number_of_images": 1,
  "triple_prompt_t5": "",
  "use_triple_prompt": false,
  "triple_prompt_clip_g": "",
  "triple_prompt_clip_l": "",
  "negative_conditioning_end": 0,
  "triple_prompt_empty_padding": true
}
Input Parameters
seed Type: integer
Set a seed for reproducibility. Random by default.
model Default: sd3_medium_incl_clips_t5xxlfp16.safetensors
Pick whether to use T5-XXL in fp16, fp8 or not at all. We recommend fp16 for this model as it has the best image quality. When running locally we recommend fp8 for lower memory usage. We've included all versions here for exploration.
shift Type: numberDefault: 3Range: 0 - 20
The timestep scheduling shift; shift values higher than 1.0 are better at managing noise in higher resolutions. Try values 6.0 and 2.0 to experiment with effects.
steps Type: integerDefault: 28
The number of steps to run the model for (more steps = better image but slower generation. Best results for this model are around 26 to 36 steps.)
width Type: integerDefault: 1024
The width of the image (best output at ~1 megapixel. Resolution must be divisible by 64)
height Type: integerDefault: 1024
The height of the image (best output at ~1 megapixel. Resolution must be divisible by 64)
prompt Type: stringDefault:
This prompt is ignored when using the triple prompt mode. See below.
sampler Default: dpmpp_2m
The sampler to use (used to manage noise)
scheduler Default: sgm_uniform
The scheduler to use (used to manage noise; do not use karras)
output_format Default: webp
Format of the output images
guidance_scale Type: numberDefault: 3.5Range: 0 - 20
The guidance scale tells the model how similar the output should be to the prompt. (Recommend between 3.5 and 4.5; if images look 'burnt,' lower the value.)
output_quality Type: integerDefault: 80Range: 0 - 100
Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.
negative_prompt Type: stringDefault:
Negative prompts do not really work in SD3. This will simply cause your output image to vary in unpredictable ways.
number_of_images Type: integerDefault: 1Range: 1 - 10
The number of images to generate
triple_prompt_t5 Type: stringDefault:
The prompt that will be passed to just the T5-XXL model.
use_triple_prompt Type: booleanDefault: false
triple_prompt_clip_g Type: stringDefault:
The prompt that will be passed to just the CLIP-G model.
triple_prompt_clip_l Type: stringDefault:
The prompt that will be passed to just the CLIP-L model.
negative_conditioning_end Type: numberDefault: 0Range: 0 - 1
When the negative conditioning should stop being applied. By default it is disabled. If you want to try a negative prompt, start with a value of 0.1
triple_prompt_empty_padding Type: booleanDefault: true
Whether to add padding for empty prompts. Useful if you only want to pass a prompt to one or two of the three text encoders. Has no effect when all prompts are filled. Disable this for interesting effects.
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Random seed set to: 2483966773
Running workflow
got prompt
Executing node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 271, title: KSampler, class type: KSampler
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:04,  5.89it/s]
  7%|▋         | 2/28 [00:00<00:06,  3.93it/s]
 11%|█         | 3/28 [00:00<00:06,  4.09it/s]
 14%|█▍        | 4/28 [00:00<00:05,  4.15it/s]
 18%|█▊        | 5/28 [00:01<00:05,  4.18it/s]
 21%|██▏       | 6/28 [00:01<00:05,  4.22it/s]
 25%|██▌       | 7/28 [00:01<00:04,  4.24it/s]
 29%|██▊       | 8/28 [00:01<00:04,  4.25it/s]
 32%|███▏      | 9/28 [00:02<00:04,  4.25it/s]
 36%|███▌      | 10/28 [00:02<00:04,  4.26it/s]
 39%|███▉      | 11/28 [00:02<00:03,  4.26it/s]
 43%|████▎     | 12/28 [00:02<00:03,  4.26it/s]
 46%|████▋     | 13/28 [00:03<00:03,  4.26it/s]
 50%|█████     | 14/28 [00:03<00:03,  4.26it/s]
 54%|█████▎    | 15/28 [00:03<00:03,  4.26it/s]
 57%|█████▋    | 16/28 [00:03<00:02,  4.26it/s]
 61%|██████    | 17/28 [00:03<00:02,  4.26it/s]
 64%|██████▍   | 18/28 [00:04<00:02,  4.26it/s]
 68%|██████▊   | 19/28 [00:04<00:02,  4.25it/s]
 71%|███████▏  | 20/28 [00:04<00:01,  4.26it/s]
 75%|███████▌  | 21/28 [00:04<00:01,  4.26it/s]
 79%|███████▊  | 22/28 [00:05<00:01,  4.25it/s]
 82%|████████▏ | 23/28 [00:05<00:01,  4.25it/s]
 86%|████████▌ | 24/28 [00:05<00:00,  4.25it/s]
 89%|████████▉ | 25/28 [00:05<00:00,  4.25it/s]
 93%|█████████▎| 26/28 [00:06<00:00,  4.25it/s]
 96%|█████████▋| 27/28 [00:06<00:00,  4.25it/s]
100%|██████████| 28/28 [00:06<00:00,  4.24it/s]
100%|██████████| 28/28 [00:06<00:00,  4.25it/s]
Executing node 231, title: VAE Decode, class type: VAEDecode
Executing node 273, title: Save Image, class type: SaveImage
Prompt executed in 7.17 seconds
outputs:  {'273': {'images': [{'filename': 'SD3_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
SD3_00001_.png
Version Details
Version ID
a9f4aebd943ad7db13de8e34debea359d5578d08f128e968f9a36c3e9b0148d4
Version Created
June 21, 2024
Run on Replicate →