Run Locally
anima-preview-flash-v2-ep100.safetensors
132 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
ANIMA · LoRAs
by levzzz - [Anima] Flash 8 steps cfg 1 distilled V2
Creator notes
a distillation lora for anima, trained on ~100 images at 1024x generated by the model itself using 40 steps cfg = 4 er_sde from diverse captions
baked-in negative prompt: worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia
may or may not be underbaked/overbaked
works best with cfg = 1 and 8 steps for heun/2s samplers, 16 steps for 1s or multistep samplers, but you can use however many steps you'd like.
the training code is a modification of diffusion-pipe for RL/distillation + custom comfyui nodes for data generation
TODO: get a larger more diverse RL dataset and filter it for artifacts
TODO: do larger ranks and 1536x training, as well as auxillary loss(es)
Update: I may have been doing dataset generation wrong the entire fucking time... ComfyUI be damned. Possible new version soon(?)
SHA256
2D73254F7B0BA0C75B7A62111FB7AF6A2EE7FCD7C96F21FBCBDDF8955FA24A74
ModelTrends.ai Model ID
#25472
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
er_sde
Steps
16
Guidance
5
Seed
2137249497
Size
1024x1280
Prompt
masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest, white outline, flat colors, square pattern background, ,halftone effect, ,
1boy, solo, alone, barley lightfoot, blue elf, blue skin, stocky body, black beanie, stubble, Dark blue hair, front view, bara, thick thighs, muscular thighs, round belly,
medium shot, , flexing, smirking, front left quarter view, standing, muscle gut, bara, toon, looking at viewer,
white frame, toon, disney eyes,
, black rock band t shirt, graphic tee, blue jean vest, jean vest, open vest, patches in vest,
Negative prompt
worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia, multiple tails, modern, recent, old, oldest, graphic, cartoon, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, very displeasing, (worst quality, bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, username, simple background, conjoined, bad ai-generated, fully standing, anime, anime eyes,
Settings
Sampler
er_sde_simple
Steps
8
Guidance
1.5
Seed
566475651328078
Size
896x1152
Weight used
1
Prompt
masterpiece, ultra-HD, very aesthetic, 8K, real,realstic,flat colors,abstract, surrealism,Sumi-e, General,
Monochrome, Ink Splash, Dark Background,
BREAK
One Woman, (Solo), Ninja, Ninja, Mask, holding katana, holding Weapon, Combat Stance, Mouth Mask, Ninja Mask, Covering Mouth, Night, Combat Pose, Black Costume, Scarf, Foreshortening, Cinematic Angle, Perspective, Action Scene, Shocking, Imminent Action, Abstract Splash of Neon Purple and Red Energy, Golden Glowing katana, black hair,blue eyes,
BREAK
Dynamic Pose, Mid-Flip, Mid-Air, Twisting Body, Legs Spread, Knees Slightly Bend, Body Arched, Upper Body Tilt, Hair Flying, Piercing Gaze, Motion Blur, Dramatic Angle,Blue Glowing Lightning, Gold Glowing Lightning,
Ninja
made of golden and blue and red and yellow and purple lightning thunder trails , lthndrtrl<lora:anima-preview-flash-v2-ep100:1.0> <lora:mygoooo_anima_runpod_grok_vl_v05:0.8>
Negative prompt
empty eyes,large breast,worst quality:1.5),(low quality:1.5),(normal quality:1.5),lowres,bad anatomy,bad hands,multiple eyebrow,(cropped),extra limb,missing limbs,deformed hands,long neck,long body,(bad hands),signature,username,artist name,conjoined fingers,deformed fingers,ugly eyes,imperfect eyes,skewed eyes,unnatural face,unnatural body,error,painting by bad-artist,Close the curtains in the room,
D,unaestheticXLv31,(worst quality:1.4),(low quality:1.4),normal quality,bad anatomy,bad hands,bad face,multiple eyebrow,extra limb,missing limbs,missing finger,deformed hands,long body,bad hands,signature,username,artist name,conjoined fingers,deformed fingers,ugly eyes,imperfect eyes,skewed eyes,unnatural face,unnatural body,error,white skirt,blurry,monochrome,,By bad artist -neg,By bad artist,colorful teeth,
Settings
Sampler
er_sde_simple
Steps
8
Guidance
1.5
Seed
94614203180973
Size
896x1152
Weight used
1
Prompt
Masterpiece, ultra-high definition, extremely beautiful, 8K, realistic, photorealistic, flat color, abstract, surrealism, ink painting, general,
monochrome, ink splatters, white background,
Break
Solo male, samurai wearing a straw hat, samurai, holding a sword, holding a weapon, fighting stance, bearded, fighting pose, traditional Japanese clothing, kimono, perspective, cinematic angle, perspective, action scene, shocking, imminent action, abstract splatters of neon purple and red energy, silver-shining sword, black hair, black eyes,
Break
Dynamic pose, twisting body, legs spread, knees slightly bent, arching back, leaning upper body, kimono sleeves fluttering, sharp gaze, motion blur, dramatic angle<lora:anima-preview-flash-v2-ep100:1.0> <lora:mygoooo_anima_runpod_grok_vl_v05:0.8>
Negative prompt
empty eyes,large breast,worst quality:1.5),(low quality:1.5),(normal quality:1.5),lowres,bad anatomy,bad hands,multiple eyebrow,(cropped),extra limb,missing limbs,deformed hands,long neck,long body,(bad hands),signature,username,artist name,conjoined fingers,deformed fingers,ugly eyes,imperfect eyes,skewed eyes,unnatural face,unnatural body,error,painting by bad-artist,Close the curtains in the room,
D,unaestheticXLv31,(worst quality:1.4),(low quality:1.4),normal quality,bad anatomy,bad hands,bad face,multiple eyebrow,extra limb,missing limbs,missing finger,deformed hands,long body,bad hands,signature,username,artist name,conjoined fingers,deformed fingers,ugly eyes,imperfect eyes,skewed eyes,unnatural face,unnatural body,error,white skirt,blurry,monochrome,,By bad artist -neg,By bad artist,colorful teeth,
Similar Models
Badges for creators
Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge.
AI Models for Image, Video & Text Generation
flash steps2 anima is a LoRA for the Anima family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Anima models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
415
Anima Models
519
Chroma Models
15
Flux Models
1,497
Flux 2 / Klein Models
1,239
MiniMax H3 Models
332
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
677
Qwen Models
20
Qwen2 Models
37
Ltx2 Models
152
Stable Diffusion 1.5 Models
7,032
Stable Diffusion XL 1.0 Models
17,383
Zimage Models
815
Wan Models
1,244

Model
Trends
.ai
© ModelTrends.ai
|
© 2026
|
All Rights Reserved



