AstolfoMix-XL (256cR-Evo / 256c-Evo / 256c / DGMIZ-AK7c / 215cR-Evo / 255c / 215c / DGMLA-216 / TGMD-192 / TGMD / TSD / TIES-SOUP / Extended-FP64 / Baseline)
Unsolved merge, even with experience on SD1 and SD2 .
See full article in Github
Since "Extended-FP64", dedicated merger sd-mecha is used. It is the SD version of mergekit .
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 . 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.
256cR-Evo
Redo of 215cR-Evo.
Current version: 256cR-Evo-AstolfoMix-1ep-25082603.safetensors
Recommended version: "25082603"
Recommended CFG: 4.0 (Euler, SEG 11.0, PAG = 1.0)
Prompt is minimal. Even empty.
251109-220461091-2016-1152-3-48-20250831122853.jpg parameters
solo, anthro, furry, astolfo, standing in front of a car branded mclaren
Steps: 48, Sampler: Euler, Schedule type: Automatic, CFG scale: 3, Seed: 220461091, Size: 1344x768, Model hash: 8117bdd7fb, Model: 256cR-Evo-AstolfoMix-1ep-25082606, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires upscaler: Latent, SEG Active: True, SEG Blur Sigma: 11, SEG Start Step: 0, SEG End Step: 2048, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 2048, Version: v1.10.1256c-Evo
Merging the trained
AstolfoXL 1EP back to 256c. Applied Git Rebasin as the "c" version.
It will be the base model of 2EP.
Current version: 256cEvo-AstolfoMix-1ep-25072103.safetensors
Recommended version: "25072103"
Recommended CFG: 4.0 (Euler, SEG 11.0, PAG = 1.0)
Prompt is minimal. Even empty.
250998-541257757-2016-1152-4-48-20250726013115.jpg parameters
(car:0), [[mclaren]], (1boy:0), [astolfo]
Steps: 48, Sampler: Euler, Schedule type: Automatic, CFG scale: 4, Seed: 541257757, Size: 1344x768, Model hash: 06a7d4855a, Model: 256cEvo-AstolfoMix-1ep-25072103, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires upscaler: Latent, SEG Active: True, SEG Blur Sigma: 11, SEG Start Step: 0, SEG End Step: 2048, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 2048, Version: v1.10.1256c
Revised from 255c. Now it is in correct base model.
Current version: x256c-AstolfoMix-25072101-a4da898.safetensors
Recommended version: "25072101"
Recommended CFG: 4.0 (Euler, SEG 11.0, PAG = 1.0)
Prompt is minimal. Even empty.
250934-1235085556-2016-1152-4-48-20250725234717.jpg parameters
(car:0), [[mclaren]], (1boy:0), [astolfo]
Steps: 48, Sampler: Euler, Schedule type: Automatic, CFG scale: 4, Seed: 1235085556, Size: 1344x768, Model hash: 388495512a, Model: x256c-AstolfoMix-25072101-a4da898, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires upscaler: Latent, SEG Active: True, SEG Blur Sigma: 11, SEG Start Step: 0, SEG End Step: 2048, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 2048, Version: v1.10.1DGMIZ-AK7c
See Git Rebasin and DGMLA in lower session.
Current version: x6c-AstolfoKarmix-25071602-5818193.safetensors
Recommended version: "25071602"
Recommended CFG: 6.0 (CFG++ , SEG 11.0, PAG = 1.0)
Prompt is minimal. Even empty.
250851-2014064198-2016-1152-6-48-20250719032909.jpg parameters
car, mclaren, anthro, furry, astolfo
Steps: 48, Sampler: DDIM CFG++, Schedule type: Automatic, CFG scale: 6, Seed: 2014064198, Size: 1344x768, Model hash: a1e7ba8eb7, Model: x6c-AstolfoKarmix-25071602-5818193, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires upscaler: Latent, SEG Active: True, SEG Blur Sigma: 11, SEG Start Step: 0, SEG End Step: 2048, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 2048, Version: v1.10.1215cR-Evo
Merging the trained
AstolfoXL 1EP back to 215c, along with a realistic LoRA. Also applied Git Rebasin as the "c" version.
Current version: 215cR-Evo-AstolfoMix-1ep-25060109.safetensors
Recommended version: "25060109"
Recommended CFG: 6.0 (CFG++ , SEG 11.0, PAG = 1.0)
Prompt is minimal. Even empty.
250647-1679148228-2016-1152-6-48-20250610225006.jpg parameters
(solo:0), (boy:0), (qipao:0.98), [astolfo_\(fate\)], [[lunar new year]], [[[[kowloon]]]]
Steps: 48, Sampler: DDIM CFG++, Schedule type: Automatic, CFG scale: 6, Seed: 1679148228, Size: 1344x768, Model hash: 1ac0f64cb1, Model: 215cR-Evo-AstolfoMix-1ep-25060109, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires upscaler: Latent, SEG Active: True, SEG Blur Sigma: 11, SEG Start Step: 0, SEG End Step: 2048, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 2048, Version: v1.10.1255c
Redo from 215c with 40 more models. Pseudorandom weights archieved.
Current version: x255c-AstolfoMix-25022801-1458190.safetensors
Recommended version: "x255c"
Recommended CFG: 6.0 (CFG++ , SEG 11.0, PAG = 1.0)
It do not listen to prompts. Recommended to train as base model.
250372-3857800394-2016-1152-6-48-20250328020251.jpg parameters
(car:0), [[mclaren]], (1boy:0), [astolfo]
Steps: 48, Sampler: DDIM CFG++, Schedule type: Automatic, CFG scale: 6, Seed: 3857800394, Size: 1344x768, Model hash: 516c1564c3, Model: x255c-AstolfoMix-25022801-1458190, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires upscaler: Latent, SEG Active: True, SEG Blur Sigma: 11, SEG Start Step: 0, SEG End Step: 2048, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 2048, Version: v1.10.1215c
Current version: x215c-AstolfoMix-24101101-6e545a3.safetensors
Recommended version: "x215c"
Recommended CFG: 6.0 (CFG++ , SEG 11.0, PAG = 1.0)
Prompt is minimal. Even empty.
241133-2004174654-2016-1152-6-48-20241201213202.jpg parameters
(car:0), [[AMG F1 W11]], (1boy:0), [astolfo]
Steps: 48, Sampler: DDIM CFG++, Schedule type: Automatic, CFG scale: 6, Seed: 2004174654, Size: 1344x768, Model hash: b31b84ff71, Model: x215c-AstolfoMix-24101101-6e545a3, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Denoising strength: 0.7, Clip skip: 2, Hires upscale: 1.5, Hires upscaler: Latent, SEG Active: True, SEG Blur Sigma: 11, SEG Start Step: 0, SEG End Step: 2048, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 2048, Version: v1.10.1DGMLA-216
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.
241135-2123095857-2688-1536-3-256-20241013140426.jpg 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: v1.10.1TGMD-192
Scaled up version from TGMD (from 117 to 192)
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.
241007-2435649982-2016-1152-3-256-20240906071641.jpg 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: v1.10.1TGMD (TIES-GeometricMedian w/ DROP)
TGMD Merge of 116 SDXL models,
unfiltered . TGMD is an algorithm modified from
Model Stock .
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.
240672-1526207600-2688-1536-3-256-20240615232306.jpg 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: v1.9.4TSD (TIES-SOUP w/ DROP)
TSD Merge of 102 SDXL models,
unfiltered . TSD is an algorithm modified from
DARE Merge (ICML 2024).
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.
240564-3134096594-2688-1536-3-256-20240513053626.jpg 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: v1.9.3TIES-SOUP
TIES-SOUP of 73 SDXL models, unfiltered. TIES-SOUP is an algorithm modified from
TIES merging (NeurIPS 2023).
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.
230748.jpg 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: v1.9.3Extended-FP64
Uniform merge 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.
240426-1841382272-2016-1152-4.5-256-20240418043456.png 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: v1.9.0Baseline
Uniform merge of 32 UNETS + (19+26) CLIPS (from 21 models). Discovered model count: 42. It is a spinoff of
Uniform Soup .
Current version: x17-AstolfoMix-x13te0x14te1.safetensors
Recommended version: "x17" for full experience, or "x11c" for human focused.
Recommended CFG: 4.5
Prompt is minimal.
240234-2213673007-2016-1152-4.5-192-20240210015331.jpg 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: v1.7.0Recipes / Model selection logs / Models involved
Round Algo Model Name RAW UNET TE0 TE1 Recipe 01 Uniform Soup x17-AstolfoMix-x13te0x14te1.safetensors42 32 14 21 json 02 Uniform Soup x43-AstolfoMix-x22te0x31te1.safetensors50 44 22 31 mecha 03 Uniform Soup x45-AstolfoMix-x39te0x39te1-e2e-240222-60d0764.safetensors52 46 40 40 mecha 04 Uniform Soup x63-AstolfoMix-x60te0x41te1-e2e-240407-feefbf4.safetensors70 52 61 42 mecha 05 TIES-SOUP x72a-AstolfoMix-240421-feefbf4.safetensors73 73 73 73 mecha 06 TIES-SOUP w/ DROP x101a-AstolfoMix-24050903-4edc67c.safetensors102 102 102 102 mecha 07 TGMD: TIES-GeometricMedian w/ DROP x116a-AstolfoMix-24060702-01823a9.safetensors117 117 117 117 mecha 08 TGMD-192: Scaled up from TGMD x191a-AstolfoMix-24083001-3360d18.safetensors192 192 192 192 mecha 09 DGMLA-216: Drop w/ GeoMedian and LA x215a-AstolfoMix-24101101-6e545a3.safetensors216 216 216 216 mecha 10 215c: Permutation from the Fermat Point x215c-AstolfoMix-24101101-6e545a3.safetensors216 216 216 216 n/a 11 255c: Scale up from 215c x255c-AstolfoMix-25022801-1458190.safetensors256 256 256 256 n/a 12 215cR-Evo: Back to basic 215cR-Evo-AstolfoMix-1ep-25060109.safetensors3 3 3 3 n/a 13 256c: Revise from 255c x256c-AstolfoMix-25072101-a4da898.safetensors257 257 257 257 n/a
DGMIZ: Compute resources for the main merge
24101502.png
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 14.0 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 250228 DGMLA 256 24 2.600 39.0 250607 DGMLA 16 2 <0.1 3 250607 DGMLA 5 2 <0.1 0.9 250607 DGMIZ 5 2 <0.1 1.5 250723 DGMIZ 257 2 0.883 41.2
215c: Compute resources for the post merge treatment
24120101.png rebasin.jpg Date Algo Model counts Threads RAM Usage (TB, FP64) Time used (Hours, Xeon 8358 x2) 241115 215c 216 1 < 0.1 9.0 250228 255c 256 48 < 0.1 1.33
215cR-Evo in nutshell
0.5 (0.5 215c + 0.5 "R Lora") + 0.5 "1EP".
DGMIZ-AK7c explained
DGMXX-XXXX: "Drop w/ GeoMedian and LA", modified from DELLA Merge and previous works.
XXXIZ-XXXX: "Iso-Z", modified from Isotropic Merge.
XXXXX-AK7X: Same model pool in AstolfoKarmix NoobAI based v1.1.
XXXXX-XXXc: "Extrapolated Re-Basin", modified from Git Re-Basin (ICLR2023?), with "2B-A" merge.
