|
--- |
|
language: |
|
- en |
|
license: creativeml-openrail-m |
|
tags: |
|
- stable-diffusion |
|
- stable-diffusion-diffusers |
|
- text-to-image |
|
- safetensors |
|
- merge |
|
inference: true |
|
thumbnail: >- |
|
https://huggingface.co/6DammK9/AstolfoMix-XL/resolve/main/241135-2123095857-2688-1536-3-256-20241013140426.jpg |
|
widget: |
|
- text: "1boy, astolfo" |
|
example_title: "astolfo" |
|
library_name: diffusers |
|
--- |
|
|
|
# AstolfoMix-XL (DGMLA-216 / TGMD-192 / TGMD / TSD / TIES-SOUP / Extended-FP64 / Baseline) # |
|
|
|
- Unsolved merge, even with experience on [SD1](https://huggingface.co/6DammK9/AstolfoMix) and [SD2](https://huggingface.co/6DammK9/AstolfoMix-SD2). |
|
- See [full article in Github](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/README_XL.MD) |
|
- Since "Extended-FP64", dedicated merger [sd-mecha](https://github.com/ljleb/sd-mecha) is used. It is the SD version of [mergekit](https://arxiv.org/abs/2403.13257). |
|
- Preview here are powered by the top session of `README.md` and converting SDXL model from A1111 standalone file into diffuers via [convert_sdxl_to_diffusers.py](https://github.com/Linaqruf/sdxl-model-converter/blob/main/convert_sdxl_to_diffusers.py). Settings may not being optimal (no CFG / PAG / FreeU etc). I'll replace the preview diffuser as soon as I upload the main model file. |
|
|
|
## DGMLA-216 ## |
|
|
|
- [DGMLA Merge](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch01/della.md#spinoff-dgmla) |
|
- [Recipe](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x215a-AstolfoMix-24101101-6e545a3.mecha), [E2E merger](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/astolfo_mix_e2e.ipynb). |
|
|
|
- Current version: `x215a-AstolfoMix-24101101-6e545a3.safetensors` |
|
- Recommended version: "x215a" |
|
- Recommended CFG: 4.5 (with CHG = 1.0), 3.0 (with PAG = 1.0) |
|
- *Prompt is minimal. Even empty.* |
|
|
|
 |
|
|
|
``` |
|
parameters |
|
|
|
[halloween], (astolfo:0.98), [[[[cemetery]]]] |
|
Steps: 256, Sampler: Euler, Schedule type: Automatic, CFG scale: 3, Seed: 2123095857, Size: 1344x768, Model hash: bdb9f136b6, Model: x215a-AstolfoMix-24101101-6e545a3, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 2, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 150, Version: v1.10.1 |
|
``` |
|
|
|
## TGMD-192 ## |
|
|
|
- Scaled up version from TGMD (from 117 to 192) |
|
- [Recipe](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x191a-AstolfoMix-24083001-3360d18.mecha), [E2E merger](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/astolfo_mix_e2e.ipynb). |
|
|
|
- Current version: `x191a-AstolfoMix-24083001-3360d18.safetensors` |
|
- Recommended version: "x191a" |
|
- Recommended CFG: 4.5 (with CHG = 1.0), 3.0 (with PAG = 1.0) |
|
- *Prompt is minimal. Even empty.* |
|
|
|
 |
|
|
|
``` |
|
parameters |
|
|
|
(car:0), [[lamborghini]], (1boy:0), [astolfo] |
|
Steps: 256, Sampler: Euler, Schedule type: Automatic, CFG scale: 3, Seed: 2435649982, Size: 1344x768, Model hash: 4c118beaa8, Model: x191a-AstolfoMix-24083001-3360d18, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 1.5, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 2048, Version: v1.10.1 |
|
``` |
|
|
|
## TGMD (TIES-GeometricMedian w/ DROP) ## |
|
|
|
- [TGMD Merge](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch01/modelstock.md#spinoff-model-stonk-by-calculate-geometric-median-with-gradient-descent) of 116 SDXL models, [unfiltered](https://wealthie.works/just-buy-the-haystack-investing-advice-that-works/). TGMD is an algorithm modified from [Model Stock](https://arxiv.org/abs/2403.19522). |
|
- [Recipe](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x116a-AstolfoMix-24060702-01823a9.mecha), [E2E merger](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/astolfo_mix_e2e.ipynb). |
|
|
|
- Current version: `x116a-AstolfoMix-24060702-01823a9.safetensors` |
|
- Recommended version: "x116a" |
|
- Recommended CFG: 4.5 (with CHG = 1.0), 3.0 (with PAG = 1.0) |
|
- *Prompt is minimal. Even empty.* |
|
|
|
 |
|
|
|
``` |
|
parameters |
|
|
|
[[striped thighhighs]], [[midriff]], [[striped shirt]], [[hoodie]], [[braid]], [astolfo], [[[[eiffel tower, france]]]] |
|
Steps: 256, Sampler: Euler, Schedule type: Automatic, CFG scale: 3, Seed: 1526207600, Size: 1344x768, Model hash: bc747cafd1, Model: x116a-AstolfoMix-24060702-01823a9, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 2, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, PAG Active: True, PAG Scale: 1, Version: v1.9.4 |
|
``` |
|
|
|
## TSD (TIES-SOUP w/ DROP) ## |
|
|
|
- [TSD Merge](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch01/dare.md#spinoff-drop-without-rescale) of 102 SDXL models, [unfiltered](https://wealthie.works/just-buy-the-haystack-investing-advice-that-works/). TSD is an algorithm modified from [DARE Merge](https://arxiv.org/abs/2311.03099) (ICML 2024). |
|
- [Recipe](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x101a-AstolfoMix-24050903-4edc67c.mecha), [E2E merger](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/astolfo_mix_e2e.ipynb). |
|
|
|
- Current version: `x101a-AstolfoMix-24050903-4edc67c.safetensors` |
|
- Recommended version: "x101a" |
|
- Recommended CFG: 4.5 (with CHG = 1.0), 3.0 (with PAG = 1.0) |
|
- *Prompt is minimal. Even empty.* |
|
|
|
 |
|
|
|
``` |
|
parameters |
|
|
|
(hippogriff:0.98), [braid], [[cape]], [[astolfo]], [[[[greece]]]] |
|
Steps: 256, Sampler: Euler, Schedule type: Automatic, CFG scale: 3, Seed: 3134096594, Size: 1344x768, Model hash: 7668681e22, Model: x101a-AstolfoMix-24050903-4edc67c, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 2, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, PAG Active: True, PAG Scale: 1, Version: v1.9.3 |
|
``` |
|
|
|
## TIES-SOUP ## |
|
|
|
- [TIES-SOUP](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch01/ties.md#spinoff-ties-soup) of 73 SDXL models, unfiltered. TIES-SOUP is an algorithm modified from [TIES merging](https://arxiv.org/abs/2306.01708) (NeurIPS 2023). |
|
- [Recipe](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x72a-AstolfoMix-240421-feefbf4.mecha), [E2E merger](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/astolfo_mix_e2e.ipynb). |
|
|
|
- Current version: `x72a-AstolfoMix-240421-feefbf4.safetensors` |
|
- Recommended version: "x72a" |
|
- Recommended CFG: 4.5 (with CHG = 1.0), 3.0 (with PAG = 1.0) |
|
- *Prompt is minimal. Even empty.* |
|
|
|
 |
|
|
|
``` |
|
parameters |
|
|
|
(car:0), [[mclaren]], [astolfo] |
|
Steps: 256, Sampler: Euler, Schedule type: Automatic, CFG scale: 3, Seed: 1504757665, Size: 1344x768, Model hash: e276a52700, Model: x72a-AstolfoMix-240421-feefbf4, VAE hash: 26cc240b77, VAE: sd_xl_base_1.0.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 1.5, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, PAG Active: True, PAG Scale: 1, Version: v1.9.3 |
|
``` |
|
|
|
## Extended-FP64 ## |
|
|
|
- [**Uniform merge**](https://arxiv.org/abs/2203.05482) of 52 UNETS + (61+42) CLIPS (from 70 models discovered). |
|
|
|
- Current version: `x51-AstolfoMix-x60te0x41te1-e2e-240407-feefbf4.safetensors` |
|
- Recommended version: "x51" |
|
- Recommended CFG: 4.5 (with CHG = 1.0), 3.0 (with PAG = 1.0) |
|
- *Prompt is minimal.* |
|
|
|
 |
|
|
|
``` |
|
parameters |
|
|
|
(car:0), [[mclaren]], (1boy:0), [astolfo] |
|
Steps: 256, Sampler: Euler, Schedule type: Automatic, CFG scale: 4.5, Seed: 1841382272, Size: 1344x768, Model hash: a52eba463d, Model: x51-AstolfoMix-x60te0x41te1-e2e-240407-feefbf4, VAE hash: 26cc240b77, VAE: sd_xl_base_1.0.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, CHG: "{'RegS': 1, 'RegR': 1, 'MaxI': 50, 'NBasis': 0, 'Reuse': 1, 'Tol': -4, 'IteSS': 1, 'ASpeed': 0.4, 'AStrength': 0.5, 'AADim': 2, 'CMode': 'More ControlNet', 'StartStep': 0, 'StopStep': 1}", FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 1.5, Hires steps: 64, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, Refiner switch by sampling steps: True, Version: v1.9.0 |
|
``` |
|
|
|
## Baseline ## |
|
|
|
- **Uniform merge** of 32 UNETS + (19+26) CLIPS (from 21 models). Discovered model count: 42. It is a spinoff of [Uniform Soup](https://arxiv.org/abs/2203.05482). |
|
|
|
- Current version: `x17-AstolfoMix-x13te0x14te1.safetensors` |
|
- Recommended version: "x17" for full experience, or "x11c" for human focused. |
|
- Recommended CFG: 4.5 |
|
- *Prompt is minimal.* |
|
|
|
 |
|
|
|
``` |
|
parameters |
|
|
|
(solo:0), (boy:0), (qipao:0.98), [astolfo_\(fate\)], [[lunar new year]], [[[[kowloon]]]] |
|
Steps: 192, Sampler: Euler, CFG scale: 4.5, Seed: 2213673007, Size: 1344x768, Model hash: 82f53a8fe1, Model: x17-AstolfoMix-x13te0x14te1, VAE hash: 26cc240b77, VAE: sd_xl_base_1.0.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, FreeU Stages: "[{\"backbone_factor\": 1.1, \"skip_factor\": 0.6}, {\"backbone_factor\": 1.2, \"skip_factor\": 0.4}]", FreeU Schedule: "0.0, 1.0, 0.0", FreeU Version: 2, Hires upscale: 1.5, Hires upscaler: Latent, Dynamic thresholding enabled: True, Mimic scale: 1, Separate Feature Channels: False, Scaling Startpoint: MEAN, Variability Measure: AD, Interpolate Phi: 0.3, Threshold percentile: 100, Version: v1.7.0 |
|
``` |
|
|
|
## Recipes / Model selection logs / Models involved ## |
|
|
|
- See [full article in Github](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/README_XL.MD) |
|
|
|
|Round|Algo|Model Name|RAW|UNET|TE0|TE1|Recipe| |
|
|---|---|---|---|---|---|---|---| |
|
|01|Uniform Soup|`x17-AstolfoMix-x13te0x14te1.safetensors`|42|32|14|21|[json](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/recipe-x39a.json)| |
|
|02|Uniform Soup|`x43-AstolfoMix-x22te0x31te1.safetensors`|50|44|22|31|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x43-AstolfoMix-x21te0x30te1-e2e-240222-60d0764.mecha)| |
|
|03|Uniform Soup|`x45-AstolfoMix-x39te0x39te1-e2e-240222-60d0764.safetensors`|52|46|40|40|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x45-AstolfoMix-x39te0x39te1-e2e-240222-60d0764.mecha)| |
|
|04|Uniform Soup|`x63-AstolfoMix-x60te0x41te1-e2e-240407-feefbf4.safetensors`|70|52|61|42|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x63-AstolfoMix-x60te0x41te1-e2e-240407-feefbf4.mecha)| |
|
|05|TIES-SOUP|`x72a-AstolfoMix-240421-feefbf4.safetensors`|73|73|73|73|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x72a-AstolfoMix-240421-feefbf4.mecha)| |
|
|06|TIES-SOUP w/ DROP|`x101a-AstolfoMix-24050903-4edc67c.safetensors`|102|102|102|102|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x101a-AstolfoMix-24050903-4edc67c.mecha)| |
|
|07|TGMD: TIES-GeometricMedian w/ DROP|`x116a-AstolfoMix-24060702-01823a9.safetensors`|117|117|117|117|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x116a-AstolfoMix-24060702-01823a9.mecha)| |
|
|08|TGMD-192: Scaled up from TGMD|`x191a-AstolfoMix-24083001-3360d18.safetensors`|192|192|192|192|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x191a-AstolfoMix-24083001-3360d18.mecha)| |
|
|09|DGMLA-216: Drop w/ GeoMedian and LA|`x215a-AstolfoMix-24101101-6e545a3.safetensors`|216|216|216|216|[mecha](https://github.com/6DammK9/nai-anime-pure-negative-prompt/blob/main/ch05/recipes/x215a-AstolfoMix-24101101-6e545a3.mecha)| |
|
|
|
## DGMLA in nutshell ## |
|
|
|
 |
|
|
|
- This algorithm should be linear a.k.a O(N) in space, and O(NlogN) in time complexity. However layerwise merging introduce some constants skewing the actual experience. |
|
|
|
|Date|Algo|Model counts|Threads|RAM Usage (TB, FP64)|Time used (Hours, Xeon 8358 x2)| |
|
|---|---|---|---|---|---| |
|
|240607|TGMD|117|16|1.214|14| |
|
|240622|TGMD|133|8|< 1.0|12.5| |
|
|240830|TGMD|192|8|1.446|41.5| |
|
|241002|DGMLA|192|16|1.452|39.1| |
|
|241006|DGMLA|20|48|0.358|2.33| |
|
|241011|DGMLA|216|48|3.500|36.2| |
|
|
