AstolfoMix-XL

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.

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: v1.10.1

256c-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.

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: v1.10.1

256c

• Revised from 255c. Now it is in correct base model.

• Recipe (256a)

• 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.

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: v1.10.1

DGMIZ-AK7c

• ISO-Z. Modified from Isotropic Merge.

• See Git Rebasin and DGMLA in lower session.

• Recipe (x6a)

• 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.

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: v1.10.1

215cR-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.

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: v1.10.1

255c

• Redo from 215c with 40 more models. Pseudorandom weights archieved.

• Recipe (255a)

• 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.

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: v1.10.1

215c

• Partial Git-Rebasin + DGMLA. Modified from Git Rebasin.

• Additonal script, Additional merger

• 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.

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: v1.10.1

DGMLA-216

• DGMLA Merge. Modified from DELLA merge.

• Recipe, E2E merger.

• 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, E2E merger.

• 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 of 116 SDXL models, unfiltered. TGMD is an algorithm modified from Model Stock.

• Recipe, E2E merger.

• 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 of 102 SDXL models, unfiltered. TSD is an algorithm modified from DARE Merge (ICML 2024).

• Recipe, E2E merger.

• 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 of 73 SDXL models, unfiltered. TIES-SOUP is an algorithm modified from TIES merging (NeurIPS 2023).

• Recipe, E2E merger.

• 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 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.

• 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

DGMIZ: Compute resources for the main merge

• 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.

215c: Compute resources for the post merge treatment

• See this article

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.