machineminded complete guide
(at edit #0)
GitHub Flavored Markdown 100.0%
TOC
Celeb AI Nudes - Getting Started
Basics
- Have a computer with a graphics card. Preferably Nvidia - AMD can work, but will be slower. The faster the better, obvs, but anything from the last 10 years with at least 8GB VRAM should work.
- Download and install a Stable Diffusion UI. Forge or Fooocus or A1111 are good for beginners. ComfyUI is a bit more advanced.
- Download Big Lust v1.6 and put it in the models subfolder.
- Download DMD2 and put it in the LoRAs subfolder.nb: DMD2 improves quality and speed of generating, at the cost of variety and prompt adherence. You must use it with certain settings (see below), and negative prompts do not work with it.
- Download celebrity LoRAs from Civitai and elsewhere. Ones trained on Big Lust work best, but any trained on SDXL will work to some extent. A few good creators to follow are MachineMinded, rustyshackleford69420 and BertyDastid.
- In SD, select Big Lust checkpoint, and your DMD2 and celebrity LoRA, then set the following settings: Steps: 7 CFG: 1.0 Sampler: lcm
- Type in what you want to see and press 'Generate'. If you get stuck, or need help, or your gens look weird, come back to the thread and post your settings. Someone might help you.
For Best Results
- Try and stick to the optimal SDXL resolutions.
- Use the bigASP tags list.
- Some LoRAs don't work well without their keywords. DMD2 doesn't have one, but most celebrity LoRAs do. Check 'trigger words' on the Civitai page, and use them in your prompts.
- Detail on faces can be dodgy sometimes, especially on wide shots. Learn to use inpainting, ADetailer, or FaceDetailer (depending on your choice of UI) to improve them.
Machineminded
Image Generation
Prerequisites
- Download and install an image generation UI of your choice (ComfyUI, Forge, Fooocus, Automatic1111, etc)
- Download bigLust_v16.safetensors from Civitai and place in the appropriate directory for your UI.
- Download the DMD2 LoRA from huggingface and place in the appropriate directory for your UI.
- Below are a Fooocus preset and a basic ComfyUI workflow for getting started.
I prefer Fooocus but the majority of users are on ComfyUI or Forge (or its variants). Below is a Fooocus preset you can place into <your-fooocus-directory>/presets/biglust16.json. You can select the preset upon starting Fooocus or provide it as a command line argument so that it's selected automatically. This will configure everything you need to generate images with bigLust_v16 and DMD2.
Fooocus Preset
{
"default_model": "bigLust_v16.safetensors",
"default_refiner": "None",
"default_refiner_switch": 0.5,
"default_loras": [
[
true,
"sd_xl_offset_example-lora_1.0.safetensors",
0.1
],
[
true,
"dmd2_sdxl_4step_lora.safetensors",
1.0
],
[
true,
"None",
1.0
],
[
true,
"None",
1.0
],
[
true,
"None",
1.0
]
],
"default_cfg_scale": 1,
"default_sample_sharpness": 2.0,
"default_sampler": "lcm",
"default_scheduler": "karras",
"default_performance": "Speed",
"default_prompt": "",
"default_prompt_negative": "",
"default_styles": [],
"default_aspect_ratio": "896*1152",
"default_overwrite_step": 7,
"embeddings_downloads": {}
}
ComfyUI Workflow (DMD2 Only)
{
"last_node_id": 16,
"last_link_id": 29,
"nodes": [
{
"id": 11,
"type": "PatchModelAddDownscale",
"pos": [
45.70000457763672,
626.6005859375
],
"size": [
529.199951171875,
202
],
"flags": {},
"order": 4,
"mode": 4,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 17
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
18
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "PatchModelAddDownscale"
},
"widgets_values": [
3,
2,
0,
0.35,
true,
"bicubic",
"bicubic"
]
},
{
"id": 10,
"type": "LoraLoader",
"pos": [
38,
444.5999755859375
],
"size": [
315,
126
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 13
},
{
"name": "clip",
"type": "CLIP",
"link": 14
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
17
],
"slot_index": 0
},
{
"name": "CLIP",
"type": "CLIP",
"links": [
15,
16
],
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "LoraLoader"
},
"widgets_values": [
"people\\taylor-swift-biglust16-v2.safetensors",
1,
1
]
},
{
"id": 2,
"type": "LoraLoader",
"pos": [
36.50000762939453,
259.1000671386719
],
"size": [
315,
126
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 5
},
{
"name": "clip",
"type": "CLIP",
"link": 7
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
13
],
"slot_index": 0
},
{
"name": "CLIP",
"type": "CLIP",
"links": [
14
],
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "LoraLoader"
},
"widgets_values": [
"dmd2_sdxl_4step_lora.safetensors",
1,
1
]
},
{
"id": 1,
"type": "CheckpointLoaderSimple",
"pos": [
35.30000305175781,
113.09999084472656
],
"size": [
315,
98
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
5
],
"slot_index": 0
},
{
"name": "CLIP",
"type": "CLIP",
"links": [
7
],
"slot_index": 1
},
{
"name": "VAE",
"type": "VAE",
"links": [
11
],
"slot_index": 2
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": [
"bigLust_v16.safetensors"
]
},
{
"id": 5,
"type": "CLIPTextEncode",
"pos": [
386.5997009277344,
364.8999938964844
],
"size": [
400,
200
],
"flags": {
"collapsed": true
},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 16
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
3
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
""
]
},
{
"id": 8,
"type": "EmptyLatentImage",
"pos": [
523.900390625,
427.29986572265625
],
"size": [
315,
106
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
4
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "EmptyLatentImage"
},
"widgets_values": [
768,
1344,
1
]
},
{
"id": 6,
"type": "KSampler",
"pos": [
844.5999755859375,
110.70008087158203
],
"size": [
377.70001220703125,
262
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 18
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 2
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 3
},
{
"name": "latent_image",
"type": "LATENT",
"link": 4
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
10
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [
834723249479022,
"randomize",
7,
1,
"lcm",
"karras",
1
]
},
{
"id": 7,
"type": "VAEDecode",
"pos": [
1241.000244140625,
120.20995330810547
],
"size": [
210,
46
],
"flags": {
"collapsed": true
},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 10
},
{
"name": "vae",
"type": "VAE",
"link": 11
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
29
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 9,
"type": "PreviewImage",
"pos": [
1410.2008056640625,
120
],
"size": [
725.3365478515625,
799.3260498046875
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 29
}
],
"outputs": [],
"properties": {
"Node name for S&R": "PreviewImage"
},
"widgets_values": []
},
{
"id": 4,
"type": "CLIPTextEncode",
"pos": [
382.4999694824219,
113.99999237060547
],
"size": [
400,
200
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 15
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
2
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"1girl, solo, taylor swift, wearing a cheerleading uniform"
]
}
],
"links": [
[
2,
4,
0,
6,
1,
"CONDITIONING"
],
[
3,
5,
0,
6,
2,
"CONDITIONING"
],
[
4,
8,
0,
6,
3,
"LATENT"
],
[
5,
1,
0,
2,
0,
"MODEL"
],
[
7,
1,
1,
2,
1,
"CLIP"
],
[
10,
6,
0,
7,
0,
"LATENT"
],
[
11,
1,
2,
7,
1,
"VAE"
],
[
13,
2,
0,
10,
0,
"MODEL"
],
[
14,
2,
1,
10,
1,
"CLIP"
],
[
15,
10,
1,
4,
0,
"CLIP"
],
[
16,
10,
1,
5,
0,
"CLIP"
],
[
17,
10,
0,
11,
0,
"MODEL"
],
[
18,
11,
0,
6,
0,
"MODEL"
],
[
29,
7,
0,
9,
0,
"IMAGE"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 0.9090909090909095,
"offset": [
501.5933221314407,
263.1868698332984
]
}
},
"version": 0.4
}
DMD2 Workflow with Facedetailer
{
"last_node_id": 16,
"last_link_id": 28,
"nodes": [
{
"id": 2,
"type": "LoraLoader",
"pos": [
42,
236
],
"size": [
315,
126
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "model",
"localized_name": "model",
"type": "MODEL",
"link": 5
},
{
"name": "clip",
"localized_name": "clip",
"type": "CLIP",
"link": 7
}
],
"outputs": [
{
"name": "MODEL",
"localized_name": "MODEL",
"type": "MODEL",
"links": [
13
],
"slot_index": 0
},
{
"name": "CLIP",
"localized_name": "CLIP",
"type": "CLIP",
"links": [
14
],
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "LoraLoader"
},
"widgets_values": [
"dmd2_sdxl_4step_lora.safetensors",
1,
1
]
},
{
"id": 9,
"type": "PreviewImage",
"pos": [
2398,
76
],
"size": [
522.6699829101562,
565.47998046875
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "images",
"localized_name": "images",
"type": "IMAGE",
"link": 20
}
],
"outputs": [],
"properties": {
"Node name for S&R": "PreviewImage"
},
"widgets_values": []
},
{
"id": 1,
"type": "CheckpointLoaderSimple",
"pos": [
43,
68
],
"size": [
315,
98
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"localized_name": "MODEL",
"type": "MODEL",
"links": [
5
],
"slot_index": 0
},
{
"name": "CLIP",
"localized_name": "CLIP",
"type": "CLIP",
"links": [
7
],
"slot_index": 1
},
{
"name": "VAE",
"localized_name": "VAE",
"type": "VAE",
"links": [
11,
23
],
"slot_index": 2
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": [
"bigLust_v16.safetensors"
]
},
{
"id": 10,
"type": "LoraLoader",
"pos": [
38,
449
],
"size": [
315,
126
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "model",
"localized_name": "model",
"type": "MODEL",
"link": 13
},
{
"name": "clip",
"localized_name": "clip",
"type": "CLIP",
"link": 14
}
],
"outputs": [
{
"name": "MODEL",
"localized_name": "MODEL",
"type": "MODEL",
"links": [
17
],
"slot_index": 0
},
{
"name": "CLIP",
"localized_name": "CLIP",
"type": "CLIP",
"links": [
15,
16,
24
],
"slot_index": 1
}
],
"properties": {
"Node name for S&R": "LoraLoader"
},
"widgets_values": [
"people\\taylor-swift-biglust16-v2.safetensors",
1,
1
]
},
{
"id": 4,
"type": "CLIPTextEncode",
"pos": [
498,
70
],
"size": [
400,
200
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "clip",
"localized_name": "clip",
"type": "CLIP",
"link": 15
}
],
"outputs": [
{
"name": "CONDITIONING",
"localized_name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
2,
25
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"1girl, solo, taylor swift, wearing a cheerleading uniform"
]
},
{
"id": 8,
"type": "EmptyLatentImage",
"pos": [
558,
655
],
"size": [
315,
106
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "LATENT",
"localized_name": "LATENT",
"type": "LATENT",
"links": [
4
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "EmptyLatentImage"
},
"widgets_values": [
768,
1344,
1
]
},
{
"id": 5,
"type": "CLIPTextEncode",
"pos": [
501,
333
],
"size": [
400,
200
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "clip",
"localized_name": "clip",
"type": "CLIP",
"link": 16
}
],
"outputs": [
{
"name": "CONDITIONING",
"localized_name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
3,
26
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
""
]
},
{
"id": 11,
"type": "PatchModelAddDownscale",
"pos": [
-105,
675
],
"size": [
529.199951171875,
202
],
"flags": {},
"order": 6,
"mode": 4,
"inputs": [
{
"name": "model",
"localized_name": "model",
"type": "MODEL",
"link": 17
}
],
"outputs": [
{
"name": "MODEL",
"localized_name": "MODEL",
"type": "MODEL",
"links": [
18,
27
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "PatchModelAddDownscale"
},
"widgets_values": [
3,
2,
0,
0.35,
true,
"bicubic",
"bicubic"
]
},
{
"id": 6,
"type": "KSampler",
"pos": [
1058,
37
],
"size": [
315,
262
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "model",
"localized_name": "model",
"type": "MODEL",
"link": 18
},
{
"name": "positive",
"localized_name": "positive",
"type": "CONDITIONING",
"link": 2
},
{
"name": "negative",
"localized_name": "negative",
"type": "CONDITIONING",
"link": 3
},
{
"name": "latent_image",
"localized_name": "latent_image",
"type": "LATENT",
"link": 4
}
],
"outputs": [
{
"name": "LATENT",
"localized_name": "LATENT",
"type": "LATENT",
"links": [
10
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [
312827419503480,
"randomize",
7,
1,
"lcm",
"karras",
1
]
},
{
"id": 7,
"type": "VAEDecode",
"pos": [
1528.099853515625,
64.1100082397461
],
"size": [
210,
46
],
"flags": {
"collapsed": true
},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "samples",
"localized_name": "samples",
"type": "LATENT",
"link": 10
},
{
"name": "vae",
"localized_name": "vae",
"type": "VAE",
"link": 11
}
],
"outputs": [
{
"name": "IMAGE",
"localized_name": "IMAGE",
"type": "IMAGE",
"links": [
19
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 16,
"type": "UltralyticsDetectorProvider",
"pos": [
1313.98046875,
534.31640625
],
"size": [
340.20001220703125,
78
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "BBOX_DETECTOR",
"localized_name": "BBOX_DETECTOR",
"type": "BBOX_DETECTOR",
"links": [
28
],
"slot_index": 0
},
{
"name": "SEGM_DETECTOR",
"localized_name": "SEGM_DETECTOR",
"type": "SEGM_DETECTOR",
"links": null
}
],
"properties": {
"Node name for S&R": "UltralyticsDetectorProvider"
},
"widgets_values": [
"bbox/face_yolov8m.pt"
]
},
{
"id": 13,
"type": "SAMLoader",
"pos": [
1355.232421875,
334.083251953125
],
"size": [
315,
82
],
"flags": {
"collapsed": false
},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "SAM_MODEL",
"localized_name": "SAM_MODEL",
"type": "SAM_MODEL",
"links": [
21
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "SAMLoader"
},
"widgets_values": [
"sam_vit_b_01ec64.pth",
"AUTO"
]
},
{
"id": 12,
"type": "FaceDetailer",
"pos": [
1794.385986328125,
84.84210205078125
],
"size": [
519,
948
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "image",
"localized_name": "image",
"type": "IMAGE",
"link": 19
},
{
"name": "model",
"localized_name": "model",
"type": "MODEL",
"link": 27
},
{
"name": "clip",
"localized_name": "clip",
"type": "CLIP",
"link": 24
},
{
"name": "vae",
"localized_name": "vae",
"type": "VAE",
"link": 23
},
{
"name": "positive",
"localized_name": "positive",
"type": "CONDITIONING",
"link": 25
},
{
"name": "negative",
"localized_name": "negative",
"type": "CONDITIONING",
"link": 26
},
{
"name": "bbox_detector",
"localized_name": "bbox_detector",
"type": "BBOX_DETECTOR",
"link": 28
},
{
"name": "sam_model_opt",
"localized_name": "sam_model_opt",
"type": "SAM_MODEL",
"shape": 7,
"link": 21
},
{
"name": "segm_detector_opt",
"localized_name": "segm_detector_opt",
"type": "SEGM_DETECTOR",
"shape": 7,
"link": null
},
{
"name": "detailer_hook",
"localized_name": "detailer_hook",
"type": "DETAILER_HOOK",
"shape": 7,
"link": null
},
{
"name": "scheduler_func_opt",
"localized_name": "scheduler_func_opt",
"type": "SCHEDULER_FUNC",
"shape": 7,
"link": null
}
],
"outputs": [
{
"name": "image",
"localized_name": "image",
"type": "IMAGE",
"links": [
20
],
"slot_index": 0
},
{
"name": "cropped_refined",
"localized_name": "cropped_refined",
"type": "IMAGE",
"shape": 6,
"links": null
},
{
"name": "cropped_enhanced_alpha",
"localized_name": "cropped_enhanced_alpha",
"type": "IMAGE",
"shape": 6,
"links": null
},
{
"name": "mask",
"localized_name": "mask",
"type": "MASK",
"links": null
},
{
"name": "detailer_pipe",
"localized_name": "detailer_pipe",
"type": "DETAILER_PIPE",
"links": null
},
{
"name": "cnet_images",
"localized_name": "cnet_images",
"type": "IMAGE",
"shape": 6,
"links": null
}
],
"properties": {
"Node name for S&R": "FaceDetailer"
},
"widgets_values": [
720,
true,
1024,
817377762813631,
"randomize",
7,
1,
"lcm",
"karras",
0.3,
5,
true,
true,
0.5,
10,
3,
"center-1",
0,
0.93,
0,
0.7,
"False",
10,
"",
2,
false,
10,
false,
false
]
}
],
"links": [
[
2,
4,
0,
6,
1,
"CONDITIONING"
],
[
3,
5,
0,
6,
2,
"CONDITIONING"
],
[
4,
8,
0,
6,
3,
"LATENT"
],
[
5,
1,
0,
2,
0,
"MODEL"
],
[
7,
1,
1,
2,
1,
"CLIP"
],
[
10,
6,
0,
7,
0,
"LATENT"
],
[
11,
1,
2,
7,
1,
"VAE"
],
[
13,
2,
0,
10,
0,
"MODEL"
],
[
14,
2,
1,
10,
1,
"CLIP"
],
[
15,
10,
1,
4,
0,
"CLIP"
],
[
16,
10,
1,
5,
0,
"CLIP"
],
[
17,
10,
0,
11,
0,
"MODEL"
],
[
18,
11,
0,
6,
0,
"MODEL"
],
[
19,
7,
0,
12,
0,
"IMAGE"
],
[
20,
12,
0,
9,
0,
"IMAGE"
],
[
21,
13,
0,
12,
7,
"SAM_MODEL"
],
[
23,
1,
2,
12,
3,
"VAE"
],
[
24,
10,
1,
12,
2,
"CLIP"
],
[
25,
4,
0,
12,
4,
"CONDITIONING"
],
[
26,
5,
0,
12,
5,
"CONDITIONING"
],
[
27,
11,
0,
12,
1,
"MODEL"
],
[
28,
16,
0,
12,
6,
"BBOX_DETECTOR"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 1.1000000000000005,
"offset": [
-944.4333298522517,
92.73696473172602
]
}
},
"version": 0.4
}
BigLust Training
- Prodigy requires a lot of VRAM.
- For these settings configure kohya_ss, or get it running on runpod.
- Download BigLust v1.6 and place it somewhere. Download BigLust v1.6 and place it somewhere. Update the "pretrained_model_name_or_path" to the path of your BigLust v1.6 model.
- Create and Curate at least 70 images. You can do more. If you get into a large number of images (> 200), consider increasing the batch size.
- High resolution images only
- No watermarks
- Variety of facial expressions and outfits from different photoshoots.
- Ensure your image folder is structed in a fashion expected by kohya. Typically I follow the pattern of <base-directory>/img/1_personname. For example /training/anne-hathaway/img/1_annehathaway.
- Calculate your total epochs by dividing 3500 into the total number of images you have. If you have 70, you would take 3500 / 70 = 50 epochs. Update the "epoch" value in your training json to that number.
- Load your configuration into kohya-gui and click start training.
I'm glossing over fine details but this should be enough to get going.
kohya_ss settings
{
"LoRA_type": "Standard",
"LyCORIS_preset": "full",
"adaptive_noise_scale": 0,
"additional_parameters": "",
"async_upload": false,
"block_alphas": "",
"block_dims": "",
"block_lr_zero_threshold": "",
"bucket_no_upscale": true,
"bucket_reso_steps": 64,
"bypass_mode": false,
"cache_latents": true,
"cache_latents_to_disk": false,
"caption_dropout_every_n_epochs": 0,
"caption_dropout_rate": 0,
"caption_extension": ".txt",
"clip_skip": 1,
"color_aug": false,
"constrain": 0,
"conv_alpha": 1,
"conv_block_alphas": "",
"conv_block_dims": "",
"conv_dim": 1,
"dataset_config": "",
"debiased_estimation_loss": false,
"decompose_both": false,
"dim_from_weights": false,
"dora_wd": false,
"down_lr_weight": "",
"dynamo_backend": "no",
"dynamo_mode": "default",
"dynamo_use_dynamic": false,
"dynamo_use_fullgraph": false,
"enable_bucket": true,
"epoch": 70,
"extra_accelerate_launch_args": "",
"factor": -1,
"flip_aug": true,
"fp8_base": false,
"full_bf16": false,
"full_fp16": false,
"gpu_ids": "",
"gradient_accumulation_steps": 1,
"gradient_checkpointing": true,
"huber_c": 0.1,
"huber_schedule": "snr",
"huggingface_path_in_repo": "",
"huggingface_repo_id": "",
"huggingface_repo_type": "",
"huggingface_repo_visibility": "",
"huggingface_token": "",
"ip_noise_gamma": 0,
"ip_noise_gamma_random_strength": false,
"keep_tokens": 0,
"learning_rate": 1,
"log_tracker_config": "",
"log_tracker_name": "",
"log_with": "",
"logging_dir": "/workspace/person-name-biglust/logs",
"loss_type": "l2",
"lr_scheduler": "cosine",
"lr_scheduler_args": "",
"lr_scheduler_num_cycles": 1,
"lr_scheduler_power": 1,
"lr_warmup": 10,
"main_process_port": 0,
"masked_loss": false,
"max_bucket_reso": 2048,
"max_data_loader_n_workers": 0,
"max_grad_norm": 1,
"max_resolution": "1024,1024",
"max_timestep": 1000,
"max_token_length": 75,
"max_train_epochs": 0,
"max_train_steps": 0,
"mem_eff_attn": false,
"metadata_author": "",
"metadata_description": "",
"metadata_license": "",
"metadata_tags": "person name",
"metadata_title": "person name",
"mid_lr_weight": "",
"min_bucket_reso": 256,
"min_snr_gamma": 5,
"min_timestep": 0,
"mixed_precision": "bf16",
"model_list": "custom",
"module_dropout": 0,
"multi_gpu": false,
"multires_noise_discount": 0.3,
"multires_noise_iterations": 0,
"network_alpha": 128,
"network_dim": 128,
"network_dropout": 0,
"network_weights": "",
"noise_offset": 0.07,
"noise_offset_random_strength": false,
"noise_offset_type": "Original",
"num_cpu_threads_per_process": 2,
"num_machines": 1,
"num_processes": 1,
"optimizer": "Prodigy",
"optimizer_args": "d_coef=0.5 safeguard_warmup=True use_bias_correction=True weight_decay=0.01 betas=(0.9,0.99)",
"output_dir": "/workspace/person-name-biglust/lora",
"output_name": "person-name-biglust16",
"persistent_data_loader_workers": false,
"pretrained_model_name_or_path": "/workspace/bigLust_v16.safetensors",
"prior_loss_weight": 1,
"random_crop": false,
"rank_dropout": 0,
"rank_dropout_scale": false,
"reg_data_dir": "",
"rescaled": false,
"resume": "",
"resume_from_huggingface": "",
"sample_every_n_epochs": 0,
"sample_every_n_steps": 100,
"sample_prompts": "iphone selfie of person name woman, 1girl, solo, yellow bra, headshot, cleavage, smirk, auburn hair --w 1024 --h 1024 --n ugly, old, weird",
"sample_sampler": "euler_a",
"save_as_bool": false,
"save_every_n_epochs": 5,
"save_every_n_steps": 0,
"save_last_n_steps": 0,
"save_last_n_steps_state": 0,
"save_model_as": "safetensors",
"save_precision": "fp16",
"save_state": false,
"save_state_on_train_end": false,
"save_state_to_huggingface": false,
"scale_v_pred_loss_like_noise_pred": false,
"scale_weight_norms": 0,
"sdxl": true,
"sdxl_cache_text_encoder_outputs": false,
"sdxl_no_half_vae": false,
"seed": 0,
"shuffle_caption": true,
"stop_text_encoder_training": 0,
"text_encoder_lr": 0,
"train_batch_size": 1,
"train_data_dir": "/workspace/img",
"train_norm": false,
"train_on_input": true,
"training_comment": "",
"unet_lr": 1,
"unit": 1,
"up_lr_weight": "",
"use_cp": false,
"use_scalar": false,
"use_tucker": false,
"v2": false,
"v_parameterization": false,
"v_pred_like_loss": 0,
"vae": "",
"vae_batch_size": 0,
"wandb_api_key": "",
"wandb_run_name": "",
"weighted_captions": false,
"xformers": "xformers"
}
BigLust Prompting Tips
BigLust 1.6 is a merge of BigASP2 and Lustify. It's mostly (60%) BigASP2, so I would focus on using these tags more than anything else, but remember that BigASP 2 also understands some natural language. There's no guarantee that the below tags will greatly impact your output. You can try adding weight to them (like this:1.3).
Character tips
When prompting your character, include the "correct" hair color and eye color, as well as body type or breast size. This can help increase the accuracy of the character in the generation.
Sample Photography Tags
Film Aesthetic
- Analog film photo
- Faded film
- Desaturated
- Vintage
- Found footage
Film Types & Effects
- 35mm photo
- Polaroid photo
- Cinemascope
- Kodachrome
- Lomography
Texture & Quality
- Grainy
- Film grain
- Stained
- Vignette
- Highly detailed
Color & Contrast
- Over saturated
- Deep contrast
- Moody
- Gorgeous
- Epic
Depth & Focus
- Shallow depth of field
- Bokeh
Overall Style
- High budget
- Low quality
- Found footage
Sample Composition Tags
- General Composition
- Rule of Thirds
- Golden Ratio
- Leading Lines
- Symmetry
- Asymmetry
- Framing
- Negative Space
- Lighting & Mood
- High-Key Lighting
- Low-Key Lighting
- Chiaroscuro
- Golden Hour
- Blue Hour
- Rim Lighting
- Perspective & Depth
- Bird’s Eye View
- Worm’s Eye View
- Forced Perspective
- Depth of Field
- Bokeh
- Vanishing Point
- Foreground, Midground, Background
- Angles & Motion
- Dutch Angle
- Motion Blur
- Panning
- Subject & Focus
- Close-Up
- Macro Shot
- Silhouette
Sample Prompts
score_9, source_photo, (attractive) [CELEB NAME] 1girl, solo, flexible pose in a jungle, Nude, sweaty skin,holding breasts, tanned skin, tan lines, slim, puffy nipples, thigh gap, realistic, depth of field, sweaty skin, wet skin, wet hair, raining, film grain, highly detailed, (full body:0.8),looking at viewer, intense stare, dim lighting, darkness, background is a detailed jungle:1.1)
score_9, [CLEEB NAME], suicidegirls, tattoos, breasts, nipples, beach, white panties, (thigh gap:1.1), very long hair, tan skin, panty pull, pubic hair
NAME, nude, full body, breasts, pale skin, pointy nipples, (1950s aesthetic, 1940s, 1960s retro, 1950s hair:1.3), black hair, smiling, red lipstick, (sexy woman:1.3), (hairy pubic hair:0.8), photoshoot, kneeling, teeth, (high heels:0.5), (studio:0.5), vibrant
LoRAs
Available LoRAs
Most have been trained on Biglust 1.6. If you see a filename suffixed with -biglust , then it was trained on Biglust 1.5. Sometimes they work with Biglust 1.6 just fine. Bolded models are new and have ✨ next to them. Trigger words: Use common-sense full names for each LoRA. Typically this would be something like "alexandria ocasio-cortez", or "tate mcrae".
A whole hugging face of celeb big lust files
Torrents (may not be seeded IDK)
Here are the magnet links in markdown format:
- alanah-pearce-biglust16.safetensors
- alexandra-daddario-000075.safetensors
- alexandria-ocasio-cortez-biglust16.safetensors
- alison-brie-biglust16-v2.safetensors
- alyson-hannigan-biglust.safetensors
- ✨ alyssa-milano-biglust16.safetensors
- amanda-bynes-biglust16-resumed.safetensors
- amanda-seyfried-biglust16-v2.safetensors
- amy-lee-evanescence-biglust16-v2.safetensors
- ana-de-armas-biglust-16-000085.safetensors
- ana-saia-biglust16.safetensors
- angela-kinsey-biglust.safetensors
- anna-kendrick-biglust16.safetensors
- anna-nicole-smith-biglust16.safetensors
- anne-hathaway-biglust16.safetensors
- anya-taylor-joy-biglust16.safetensors
- ariana-grande-biglust16.safetensors
- ariana-grande-biglust16-v2.safetensors
- aubrey-plaza-biglust16-resumed.safetensors
- avril-lavigne-biglust16.safetensors
- bhad-bhabie-biglust16.safetensors
- billie-eilish-000075.safetensors
- brenda-song-biglust16.safetensors
- brie-larson-biglust16.safetensors
- britney-spears-biglust.safetensors
- candace-owens-biglust16.safetensors
- charli-damelio-biglust16.safetensors
- christina-aguilera-biglust.safetensors
- cindy-crawford-biglust16.safetensors
- cobie-smulders-biglust16.safetensors
- daisy-ridley-dalle-biglust16.safetensors
- dua-lipa-biglust16.safetensors
- elle-fanning-biglust16.safetensors
- emma-roberts-biglust16.safetensors
- emma-stone-2012-biglust16.safetensors
- emma-watson-biglust16.safetensors
- emma-watson-biglust16_v3.safetensors
- gal-gadot-biglust16.safetensors
- gillian-anderson-biglust16.safetensors
- gillian-jacobs-biglust16.safetensors
- gwen-stefani-biglust16.safetensors
- hayden-panettiere-biglust16.safetensors
- hayley-williams-biglust16.safetensors
- jenna-fischer-biglust.safetensors
- jenna-fischer-biglust16.safetensors
- jenna-fischer-biglust16-v2.safetensors
- jenna-ortega-biglust16.safetensors
- jennifer-connelly-biglust16.safetensors
- jessica-simpson-biglust16.safetensors
- kate-bosworth-biglust16.safetensors
- kate-middleton-biglust16-resumed.safetensors
- kate-middleton-biglust-resumed.safetensors
- katy-perry-biglust16.safetensors
- kiernan-shipka-biglust16.safetensors
- kristen-bell-biglust16.safetensors
- lady-gaga-biglust16-resumed.safetensors
- leanbeefpatty-biglust16.safetensors
- lea-thompson-biglust16.safetensors
- lindsay-lohan-biglust16.safetensors
- melissa-fumero-biglust16-000050.safetensors
- michelle-trachtenberg-biglust16-v2.safetensors
- mila-kunis-biglust16-resumed.safetensors
- miley-cyrus-biglust16-v2-batch4-000010.safetensors
- natalie-morales-biglust16-resumed.safetensors
- natalie-portman-biglust16.safetensors
- ✨ nicki-minaj-biglust16.safetensors
- olivia-rodrigo-biglust16.safetensors
- olivia-rodrigo-biglust16-v2.safetensors
- pamela-anderson-biglust16.safetensors
- pokimane-biglust16.safetensors
- princess-diana-90s-biglust16-000100.safetensors
- princess-diana-biglust.safetensors
- princess-diana-biglust16.safetensors
- rashida-jones-biglust16-v2.safetensors
- sabrina-carpenter-biglust16.safetensors
- sarah-chalke-biglust.safetensors
- sarah-chalke-biglust16.safetensors
- scarlett-johansson-biglust16.safetensors
- sydney-sweeney-biglust16-000010.safetensors
- taylor-swift-biglust16.safetensors
- taylor-swift-biglust16-v2.safetensors
- ✨ taylor-swift-biglust16-v3.1-000100.safetensors
- victoria-justice-biglust16.safetensors
- zooey-deschanel-biglust16.safetensors
Civitai Creators
- diaryph
- MKUltra2025
- __deep
- toxicmuffin
- rustyshackleford69420
- lonely_individual_123
- cptdan
- BertyDastid
- jc7890
- DRZ3000
- ThatsARepost
- aihotgirls
- MachineMinded
Commissions
I'll gladly do commissions or custom LoRAs. You just need to provide a high-resolution dataset of at least 70 images no less than 1024x1024. It can be done with fewer, but understand this affects the outputs of the generations. I've done some with as few as 25 images that turned out decent enough, just keep in mind that it creates limitations.
Can also be reached out on discord, username is "machineminded."
Donations / Support
I don't like begging for money, but it does help fund my machine learning hobbies.
BTC Wallet Address:
35m5mn4CMt8YPxwun33w9v3Dm1es9ZFGg4
Monero:
43oXLBVhSrHfMqutPGrZbK33sMNquxwVrHkYi4ok7LgoM32V2qC4hkpHjt13EwpcRMSZ2nU9nrZuoL4VFdxRYkX3PS5gmwm
For the (me) recompiler:
I only use Monero:
879WXAcGEpc6CjdVc1mLR6HzsnV9ps9MbPFYPb6ukGJdVWug3wSv5EbdWynPySRFgqXYJkGyT1roZDWDKsDBdPmzPeU4Q3a