Versions: <a target="_blank" rel="ugc" href="https://civarchive.com/models/10003?modelVersionId=55299">LORA SD1.5</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/10003?modelVersionId=53525">LORA SD 2.1-768</a> | <a target="_blank" rel="ugc" href="https://civarchive.com/models/10003?modelVersionId=57377">LYCORIS SD2.1-768</a>Zenkai System Explained: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/199">https://civarchive.com/articles/199</a>Beta1 sub models, models can be conditioned to provide additional flavours.<ul><li>Zenkai Ultra Hermit released 30 April 2023 variation weights using my oldest successful recipe</li><li>Zenkai Ultra Shift TBA variation using a new recipe</li><li>Zenkai Ultra Instinct TBA variation using newest recipe</li></ul> JDZ Beta1 - 22 April 2023 Beta1 is released for testing and evaluation. While convergence was reached, there are 230 styles/concepts contained within. This was trained on my original datasets used to create many CKPT / LORA already released on Civit. The Training Data contains combined instructions on making the most from this new versatile model format. UPDATE - added new "combined-instructions.zip" now includes Instructions.txt and wildcards.zip. Wildcards are now included for use with Dynamic prompts.JDZ-CaptionList.txt - ~5000 Example prompts used in captioning the 230 sets JDZ-StyleTriggers.txt - ~230 "Trigger words" used for each styleJDZenkai-GenPrompts2200.txt - ~4200 "GPT2 Generated Prompts" trained on the Caption List<img src="https://i.gyazo.com/bece2282756ca05fa00ae5a7eb9f3f9a.png" />(Above pictured) Wildcard files now included <ul><li>Future releases will be trained to Epoch 40 (~200,000 steps)</li><li>The Beta1 model is currently trained to Epoch 19 (~97000 steps.</li><li>There are many ways to use this model as it contained all my CKPT styles in one model. </li></ul><ol><li>You do not need to use Triggers and can prompt normally.</li><li>You can prompt using words listed in DJZ-Styletriggers.txt to anchor to a specific style, or use multiple triggers with attention weighting to control the output.</li><li>You can use one or more prompts as shown in the DJZ-CaptionList.txt.</li><li>You can use the DJZ-CaptionList.txt and/or JDZenkai-GenPrompts2200.txt as a wildcard with Dynamic Prompts, simply place it into the /wildcards/ folder and rename it to your choosing. I trained a GPT2 Generator which created many variations on the Example Prompts, an example of these are the JDZenkai-GenPrompts2200.txt</li></ol>This is an ongoing project so expect a LORA version next. It will take some time to create the LORA version due to a difference in the captioning. This is trained using a Parallel Dreambooth Method which prevents concept/style bleeding, but you can still mix by interpolating trained terms/triggers in the prompt. TLDR there is a missing comma, can you find it?

Johnson Diffusion Zenkai

Beta 1 is trained to 45% of the Target, for evaluation. While Convergence has been achieved, there are over 230 Styles/Concepts contained within.

johnsonDiffusion_beta1.safetensors

johnsonDiffusion_beta1_trainingData.zip

Beta1

ZenkaiUltraInstinct-Beta1

ZenkaiUltraShift-beta1

UltraHermit-Beta1

For Flux1 Schnell users: you do not need the Lora, just the .txt training data <div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/onO_a7ImrOQ" start="0"></iframe></div><a target="_blank" rel="ugc" href="https://civarchive.com/models/308724">click here if you are looking for SDXL (Beta3 version)</a> BASE MODEL: <a target="_blank" rel="ugc" href="https://civarchive.com/models/47355/johnson-diffusion-zenkai">Johnson Diffusion Zenkai</a>Zenkai System Explained: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/199">https://civarchive.com/articles/199</a>Update 24th May '23 - Added "DesuZenkaiV21beta2-lycoris" (beta2) Update 21st May '23 - Added "djzJohnsonDesuZenkaiV15-lycoris" (beta1)Animate Diff V2 video:<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/KUFex-re0kM" start="0"></iframe></div>all new version built on the Johnson Diffusion "Zenkai" Dataset Note: Beta1 contained 230 style models Beta2 contains 350 style modelsFull Instructions, Prompt Examples, Caption lists and Wildcard Files added to Training Data section for both CKPT and LORA version.The Zenkai System allow for easy interpolation of 230 of my original styles, multiplied by 5000 original prompts &amp; 4200 generated variation prompts which can be mixed, doubled or tripled and used with txt2img or img2img with ease. Art by Pure chance or by exact design. Your Choice. -------------------------------------------ALL BELOW IS OLD 108 LORA VERSION ------------------------------------------- Update: 24th Feb '23 - Added "djzJohnsonDesuV21-320" same as below, version 1, built on SD 2.1-768 with LORA 320. Update: 23rd Feb '23 - Added "djzJohnsonDesuV15-320" same as below, version 1, built on SD 1.5 with LORA 320. Update: 22nd Feb '23 - Added "djzJohnsonDesuV21-256" same as below, version 1, built on SD 2.1-768 with LORA 256. Update: 18th Feb '23 - Added "djzJohnsonDesuV15" same as below, version 1, built on SD1.5 with LORA 128. This is "djzJohnsonDesuV2" The result of retraining all of the djz Diffusion collection into a single LORA 128. While this contains the original 108 tokens, you do not need to use them and can prompt normally. While this is 250gb of models in a 200mb filesize, this will produce different images than other LORA or the original models. be sure to scroll down and get the links for the negative embeddings used to create the demo pics ;) Version 1:108 Concepts, 4277 images.<ul><li>Epoch 1 - 42,770 Steps</li><li>Epoch 2 - 85,540 Steps</li></ul>Links to recommended LORA/Negative Embeds below Epoch 1 &amp; Epoch 2 both gave nice and unique images, so we are releasing both versions.LORA 128 Demo Epoch 1 vs Epoch 2 vs Base only (same prompt/seed)<img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/efe567a9-1bfb-47d9-0d2a-8f1286eac200/width=525" /><img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b5ec76b6-da02-43a2-5c90-2fe281b75600/width=525" /><img src="https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b048c0eb-9c3a-44d4-a6e6-de4c9faed100/width=525" /> Resources we use with our SD2.1-768 models: nfixer, nartfixer, nfixernext - from Illuminati Diffusion <a target="_blank" rel="ugc" href="https://huggingface.co/IlluminatiAI/Illuminati_Diffusion_v1.0/tree/main/embeds/negative">https://huggingface.co/IlluminatiAI/Illuminati_Diffusion_v1.0/tree/main/embeds/negative</a> Neg_Facelift768 by SoCalGuitarist <a target="_blank" rel="ugc" href="https://civarchive.com/models/2385/socalguitarists-magic-facelift-negative-embedding-for-model-2x-fix-yo-ugly-faces">https://civarchive.com/models/2385/socalguitarists-magic-facelift-negative-embedding-for-model-2x-fix-yo-ugly-faces</a>DrD_PNTE768 by Dr.Diffusion<a target="_blank" rel="ugc" href="https://civarchive.com/models/4044/doctor-diffusions-point-e-negative-embedding">https://civarchive.com/models/4044/doctor-diffusions-point-e-negative-embedding</a> DangerGoose by Drift Johnson <a target="_blank" rel="ugc" href="https://civarchive.com/models/8107/djz-johnsons-image-helper-dangerhawk-and-dangergoose">https://civarchive.com/models/8107/djz-johnsons-image-helper-dangerhawk-and-dangergoose</a> Contrast Fix &amp; High Key by theOvercomer8 (style LORA)<a target="_blank" rel="ugc" href="https://civarchive.com/models/8765/theovercomer8s-contrast-fix-sd21-768">https://civarchive.com/models/8765/theovercomer8s-contrast-fix-sd21-768</a> <a target="_blank" rel="ugc" href="https://civarchive.com/models/9205/to8s-high-key-lora-sd21-768">https://civarchive.com/models/9205/to8s-high-key-lora-sd21-768</a> Resources we use with our SD1.5 models: DangerHawk by Drift Johnson<a target="_blank" rel="ugc" href="https://civarchive.com/models/8107/djz-johnsons-image-helper-dangerhawk-and-dangergoose">https://civarchive.com/models/8107/djz-johnsons-image-helper-dangerhawk-and-dangergoose</a><a target="_blank" rel="ugc" href="https://tensor.art/u/610849640887121192">https://tensor.art/u/610849640887121192</a>

Files with SHA256: 72470ca5522d2bcee5b26db40988e2eb2bce8ada10a339e83f3e80b0ba60b9d0