LoraD

KponyStandardVAE_v1.safetensors

zImage4XUPSCALERBy_zit.safetensors

sdd0_01_epoch_10.safetensors

decoder.pt

2587328_training_data.zip

zImageTurboVAE_v10.safetensors

v1.1.1

v1.0

V1.0.0

FLUX_VAE_W1_bf16.safetensors

clip_l.safetensors

Kam1.5ponyStandardVAE_v1.safetensors

letsdo.safetensors

agent-deck-main.zip

image_z_image_turbo (1).json

v1.1.0

<h3 id="letrehozott-fajlok-(a-homeworkdirartifacts-mappaban):">Létrehozott fájlok (a /home/workdir/artifacts/ mappában):</h3><ol><li>captions <a target="_blank" rel="ugc" href="http://Zimagera.zip">Zimagera.zip</a><ul><li>20 db .txt fájl (IMG_9179–9198)</li><li>Minden captionben a bebaP → Zimagera cserélve</li><li>Formátum változatlan (ugyanaz a részletes leírás + minőségi tag-ek)</li></ul></li><li>Zimagera pony <a target="_blank" rel="ugc" href="http://dataset.zip">dataset.zip</a><ul><li>Zimagera_pony/ mappa</li><li>8 db kiválasztott kép + hozzá tartozó .txt fájl</li><li>Minden captionben a bebaP → Zimagera cserélve</li><li>Ugyanaz a pony-stílusú formátum (score_9, score_8_up, ... source_realistic, Zimagera, ...)</li></ul></li></ol><h3></h3>

NBMI

Létrehozott fájlok (a /home/workdir/artifacts/ mappában):<ol><li>captions <a target="_blank" rel="ugc" href="http://Zimagera.zip">Zimagera.zip</a><ul><li>20 db .txt fájl (IMG_9179–9198)</li><li>Minden captionben a bebaP → Zimagera cserélve</li><li>Formátum változatlan (ugyanaz a részletes leírás + minőségi tag-ek)</li></ul></li><li>Zimagera pony <a target="_blank" rel="ugc" href="http://dataset.zip">dataset.zip</a><ul><li>Zimagera_pony/ mappa</li><li>8 db kiválasztott kép + hozzá tartozó .txt fájl</li><li>Minden captionben a bebaP → Zimagera cserélve</li><li>Ugyanaz a pony-stílusú formátum (score_9, score_8_up, ... source_realistic, Zimagera, ...)</li></ul></li></ol>

clip_l (1).safetensors

Zimagera pony dataset.zip

v1.2.1

upscalerV

upscalerv_v10.safetensors

Z Image 4X UPSCALER by Helaman {this is not LoRA.} <span style="background-color:rgb(23, 23, 30);color:rgb(243, 242, 253);font-family:__Inter_611a59, __Inter_Fallback_611a59, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, helvetica, arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;;font-size:medium">4x photo upscaler which handles jpg compression. This model will preserve noise. <span style="background-color:rgb(23, 23, 30);color:rgb(243, 242, 253);font-family:__Inter_611a59, __Inter_Fallback_611a59, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, helvetica, arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;;font-size:medium">General upscaler: Realistic - Restoration <span style="background-color:rgb(23, 23, 30);color:rgb(243, 242, 253);font-family:__Inter_611a59, __Inter_Fallback_611a59, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, helvetica, arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;;font-size:medium">Training details: AdamW optimizer with U-Net SN discriminator and BFloat16. Degraded with otf jpg compression down to 40, re-compression down to 40, together with resizes and the blur kernels. <span style="background-color:rgb(23, 23, 30);color:rgb(243, 242, 253);font-family:__Inter_611a59, __Inter_Fallback_611a59, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, helvetica, arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;;font-size:medium">Losses: PixelLoss using CHC (Clipped Huber with Cosine Similarity Loss), PerceptualLoss using Huber, GANLoss, <a target="_blank" rel="ugc" href="https://github.com/csjliang/LDL">LDL</a><span style="background-color:rgb(23, 23, 30);color:rgb(243, 242, 253);font-family:__Inter_611a59, __Inter_Fallback_611a59, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, helvetica, arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;;font-size:medium"> using Huber, YCbCr Color Loss (bt601) and Luma Loss (CIE XYZ) on <a target="_blank" rel="ugc" href="https://github.com/muslll/neosr">neosr</a><span style="background-color:rgb(23, 23, 30);color:rgb(243, 242, 253);font-family:__Inter_611a59, __Inter_Fallback_611a59, -apple-system, blinkmacsystemfont, &quot;Segoe UI&quot;, helvetica, arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;, &quot;Segoe UI Symbol&quot;;font-size:medium">. ComfyUI/ └── models/ ├── upscale_models └── 4xZImageTurbo_upscaler_255.safetensors <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/91cf40dd-6bf1-4179-9b71-a1b509d03dca/original=true/91cf40dd-6bf1-4179-9b71-a1b509d03dca.jpeg" /> CREDIT: <a target="_blank" rel="ugc" href="https://github.com/Phhofm/models/releases/4xNomos8k_atd_jpg">https://github.com/Phhofm/models/releases/4xNomos8k_atd_jpg</a>

Z Image 4X UPSCALER by Helaman

License: CC BY 4.0 Dataset: nomos8k Number of train images: 8492 OTF Training: Yes Pretrained_Model_G: 003_ATD_SRx4_finetune

Files with SHA256: 009671cec5a384db31052b52e344e5989b0c51a5ad4d25a8c2c629f658754d13