Name: Slime Girl Concept
Rating: 5 (2190 reviews)
Author: motimalu

Save a price and reuse it. Let a price change on its own, by time, by purchase count, or by how much it has earned. We're also proposing to retire donation goals. Tell us where we've got it wrong.

Proposal: Price Tags and Price Steps

We're a Day-0 launch partner for MiniMax H3, a next-gen open-weights multimodal video model - and it's already in the generator. No waitlist. Open weights land in a few days.

MiniMax H3 is live: open-weights video, generate now

<h1 id="slime-girl-concept-tlt3eblwd">Slime Girl Concept</h1>Just some friendly slime girls of all different types and colors. ꒷꒦ℹ️ LoRA work best when applied to the base models on which they are trained. Please read the About This Version on the appropriate base models and workflow/training information.<h3 id="license-92mggm3y8">License</h3><a target="_blank" rel="ugc" href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a>

Trained on <a target="_blank" rel="ugc" href="https://civitai.com/models/795765/illustrious-xl">Illustrious XL 0.1</a>With an updated dataset:<ul><li>919 images</li><li>manually rated <code>masterpiece, best quality, very aesthetic</code> tags</li><li>tagged <code>nsfw</code> <code>explicit</code> with imgutils anime_rating</li><li>included a small <code>water dress</code> concept dataset</li></ul>

v1.0 [Illustrious]

Trained on <a target="_blank" rel="ugc" href="https://huggingface.co/Qwen/Qwen-Image">Qwen Image</a>Using the default <a target="_blank" rel="ugc" href="https://github.com/tdrussell/diffusion-pipe/blob/4a61bcfd82eb8d54a807ac7a15f548fab73ae5e1/examples/qwen_image_24gb_vram.toml">diffusion-pipe qwen config</a>Dataset resolution of 640Previews generated with the lightx2v Lighting 4step LoRA:<a target="_blank" rel="ugc" href="https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0.safetensors">https://huggingface.co/lightx2v/Qwen-Image-Lightning/blob/main/Qwen-Image-Lightning-4steps-V1.0.safetensors</a>

v1.0 [qwen]

[WAN 14B] LoRA<ul><li>Trained with <a target="_blank" rel="ugc" href="https://github.com/tdrussell/diffusion-pipe">diffusion-pipe</a> on <a target="_blank" rel="ugc" href="https://huggingface.co/Wan-AI/Wan2.1-T2V-14B">Wan2.1-T2V-14B</a></li><li>Seems usable for both text-to-video and image-to-video workflows with Wan</li><li>Text to Video previews generated with <a target="_blank" rel="ugc" href="https://comfyanonymous.github.io/ComfyUI_examples/wan/#text-to-video">ComfyUI_examples/wan/#text-to-video</a><ul><li>Loading the LoRA with LoraLoaderModelOnly node and using the fp8 14B <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_t2v_14B_fp8_scaled.safetensors">wan2.1_t2v_14B_fp8_scaled.safetensors</a></li></ul></li><li>Image to Video previews generated with <a target="_blank" rel="ugc" href="https://comfyanonymous.github.io/ComfyUI_examples/wan/#image-to-video">ComfyUI_examples/wan/#image-to-video</a><ul><li>Using image generations from the IL/Noobai versions of this model card</li></ul></li></ul>

v1.0 [wan-t2v-14b]

Brings slimes to life in Hunyuan T2V generations!Trained with <a target="_blank" rel="ugc" href="https://github.com/tdrussell/diffusion-pipe">https://github.com/tdrussell/diffusion-pipe</a>Training data is small combination of:<ul><li>Images used from other versions this model card</li><li>Images extracted as keyframes from several videos</li><li>Short video clips ~40 frames each</li></ul>Training configs:dataset.toml<pre><code># Aspect ratio bucketing settings
enable_ar_bucket = true
min_ar = 0.5
max_ar = 2.0
num_ar_buckets = 7

[[directory]] # IMAGES
# Path to the directory containing images and their corresponding caption files.
path = '/mnt/d/huanvideo/training_data/images'
num_repeats = 5
resolutions = [1024]
frame_buckets = [1] # Use 1 frame for images.


[[directory]] # VIDEOS
# Path to the directory containing videos and their corresponding caption files.
path = '/mnt/d/huanvideo/training_data/videos'
num_repeats = 5
resolutions = [256] # Set video resolution to 256 (e.g., 244p).
frame_buckets = [33, 49, 81] # Define frame buckets for videos.</code></pre>config.toml<pre><code># Dataset config file.
output_dir = '/mnt/d/huanvideo/training_output'
dataset = 'dataset.toml'

# Training settings
epochs = 50
micro_batch_size_per_gpu = 1
pipeline_stages = 1
gradient_accumulation_steps = 4
gradient_clipping = 1.0
warmup_steps = 100

# eval settings
eval_every_n_epochs = 5
eval_before_first_step = true
eval_micro_batch_size_per_gpu = 1
eval_gradient_accumulation_steps = 1

# misc settings
save_every_n_epochs = 15
checkpoint_every_n_minutes = 30
activation_checkpointing = true
partition_method = 'parameters'
save_dtype = 'bfloat16'
caching_batch_size = 1
steps_per_print = 1
video_clip_mode = 'single_middle'

[model]
type = 'hunyuan-video'

transformer_path = '/mnt/d/huanvideo/models/diffusion_models/hunyuan_video_720_cfgdistill_fp8_e4m3fn.safetensors'
vae_path = '/mnt/d/huanvideo/models/vae/hunyuan_video_vae_bf16.safetensors'
llm_path = '/mnt/d/huanvideo/models/llm'
clip_path = '/mnt/d/huanvideo/models/clip'

dtype = 'bfloat16'
transformer_dtype = 'float8'
timestep_sample_method = 'logit_normal'

[adapter]
type = 'lora'
rank = 32
dtype = 'bfloat16'

[optimizer]
type = 'adamw_optimi'
lr = 5e-5
betas = [0.9, 0.99]
weight_decay = 0.02
eps = 1e-8</code></pre>

v1.0 [hunyuan]

v1.0 [Pony]

<pre><code>「・・・おや！？ スライムのようすが・・・！」</code></pre>Slime girls are evolving!Experimental version trained on AutismMix with an expanded dataset including generated images.Faces will tend not to hold the slime skin colors, but I think they look quite nice, and not a bad trade off for some of the other improvements to style, quality, and the <code>translucent skin</code> concept.