*Important, please read this before using the model because this is very experimental, as I am still trying to fine the optimal settings, and will slowly exit beta as the training become more stableYou can download the clip text encoder here: <a target="_blank" rel="ugc" href="https://huggingface.co/suzushi/miso-diffusion-m-1.0">https://huggingface.co/suzushi/miso-diffusion-m-1.0</a>I will write 2 articles soon as well on the details of the model.Miso Diffusion M 1.0 is an attempt to fine tune stable diffusion 3.5 medium on anime dataset. In comfy ui it uses as little as 2.4 gb vram without the t5 text encoder. This version is a step up from previous version (beta), trained on the same 160k image for 3 more epoch then fine tuned on 600k images for another 2 epoch. (2 was choosen as further training would cause it to generate more artifact and blurry images)Recommanded setting, euler, cfg:5 , 28-40 steps, (denoise: 0.95 or 1 )prompt: danbooru style tagging. I recommand simply generating with a batch size of 4 to 8 and pick the best one. It will struggle with hands and complex pose, you can add upper body so it doesnt generate full body.Quality tag<pre><code>Masterpiece, Perfect Quality, High quality, Normal Quality, Low quality</code></pre>Aesthetic Tag<pre><code>Very Aesthetic, aesthetic</code></pre>Pleasent<pre><code>Very pleasent, pleasent, unpleasent</code></pre>Additional tag: high resolution, elegantTraining was done in 1024x1024, though since the model natively supports 1440, certain prompt would work on 1440x1440 as well<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6b4cfdc7-8708-4cab-b024-d9329f71ecca/width=525/6b4cfdc7-8708-4cab-b024-d9329f71ecca.jpeg" />Training is done on gh200 with 96gb vramTraining setting: Adafactor with a batchsize of 40, lr_scheduler: cosineSD3.5 Specific setting:enable_scaled_pos_embed = truepos_emb_random_crop_rate = 0.2weighting_scheme = "flow"learning_rate = 3e-6learning_rate_te1 = 2e-6learning_rate_te2 = 2e-6Train Clip: true, Train t5xxl: falseDeveloping a base model is costly, so if you like mywork please consider donation, thanks a lot: <a target="_blank" rel="ugc" href="https://ko-fi.com/suzushi2024">https://ko-fi.com/suzushi2024</a>

Files with SHA256: 629d9f88749b5ac60dfe35a2389d5beb5bb74c9df67657048f20636bec968d67