Model
Trends
.ai
Model
Trends
.ai
nejlepší open source AI modely
Spustit lokálně
yiffymix_v44_474201.ckpt
1.99 GB · PickleTensor · fp16 · full
yiffymix_v44_474209.safetensors
3.97 GB · SafeTensor · fp32 · full
Stáhnout
yiffymix_v44_474126.ckpt
3.97 GB · PickleTensor · fp32 · full
Stáhnout
yiffymix_v44_474202.safetensors
1.99 GB · SafeTensor · fp16 · full
Stáhnout
yiffymix_v44.yaml
Other
Stáhnout
furception_vae_1-0.safetensors
319 MB · SafeTensor
Stáhnout
Stahování zajišťuje Civitai. Někteří autoři vyžadují nejprve přihlášení na Civitai.
AD
<yiffymix42>
O tomto modelu
STABLE DIFFUSION 1.5 · Základní modely
Vytvořil
chilon249
na Civitai
Poznámky autora
Use (no underscore), Artist tag very effective in YiffyMix. & Recommend & . Example Setting (Use recommended sampler to get correct quality) Setting SDXL (SDXL-lightning & NoobXL) - Steps = 12~24 - Sampler = "DDPM", "Euler A SGMUniform", "Euler SGMUniform" - CFG scale = 3~4 - Negative embeddings SDXL = , (You don't really need this) - Postive LoRA SDXL = (You don't really need this) - Stop at CLIP layers = 2 Setting SD 1.5 + vpred - Steps = 30~40 - Sampler = "DPM++ 2M Karras", "DPM++ SDE Karras", "DDIM", "UniPC" - CFG scale = 6~8 - Negative embeddings = , [SD-WebUI\embeddings] - Stop at CLIP layers = 1 - SD VAE = [SD-WebUI\models\VAE] Hires. fix - Hires steps = Steps * Denoising strength - Denoising strength = 0.25 - Hires upscaler = [SD-WebUI\models\ESRGAN] ControlNet - ControlNet = softedge_hed, - ControlNet SDXL = softedge_hed, - ControlNet Weight = 0.35~0.5 - ControlNet Pixel Perfect = true Wan 2.2 ComfyUI Animeted [] - model = - clip = / - vae = - lora (turbo) = - lora (furry-nsfw) = - lora (livewallpaper) = - sampler = steps:4, cfg:1, sampler:"eular_ancestral", schedule:"sgm_uniform" SD WebUI - - - LoRA Training SDXL - imgs count = 15~50 - total steps = epoch * imgs count * folder loop = 3000~4500 - network_dim = 64 - network_alpha = 128 (SDXL) \ 16 (Noob) - learning_rate = 0.0002~0.0005 - unet_lr = 0.0001 #learning_rate/2 - text_encoder_lr = 0.00005 #learning_rate/4 - lr_scheduler = "cosine_with_restarts" - mixed_precision = "bf16" - optimizer_type = "Adafactor" - optimizer_args = [ "scale_parameter=False", "relative_step=False", "warmup_init=False", ] YiffyMix v4x V-pred Setting # YiffyMix v4x A1111 SD-WebUI or Forge V-pred Setting 1.Download config file ".yaml" paste next to the model. 2.Raname ".yaml" same as model name. ( check the ".yaml" has [parameterization: "v"] line ) 3.Restart SD-WebUI ( if config fails to load, the model just generate noise ) # YiffyMix v4x ComfyUI or StableSwarmUI V-pred Setting Add node "ModelSamplingDiscrete", Sampling = "v_prediction" # ComfyUI V-pred Setting (old version) 1.Copy config ".yaml" to [ComfyUI\models\configs] and refresh ComfyUI 2."Load Checkpoint (With Config)" [Right Click\AddNode\advanced\model_merging] workflow:[Load Checkpoint (With Config)]-[KSampler]-[VAE Decode]-[Save Image] # v-pred mode troubleshoot If you use new version webui-forge and . Try update webui-forge (click update.bat). When loading v-pred model, you will see this line in cmd console: left over keys: dict_keys(['v_pred']) # v4.x some time will get little fried issue image in this case Use "Dynamic Prompts with __wildcards__ prompts" and "batch size > 1" Just generate again with same prompts with parament, it will return normal. Version Info v1.x [2D,512~768] old model, unstable, low resolution v2.x [2D,512~896] e621 dataset + 30~40% SD5 dataset v3.0 [2D,3D,512~1088] large dataset then v2.x version, can do 2D, 3D v3.1 [2D,3D,Real,512~1088] more realistic, but loss some concept (e621 tag count lower 1000) v3.2 [2D,3D,Real,512~1088] unstable version, use SNR version FluffyRock, more noise detail v3.3 [2D,3D,Real,512~1088] stable version, more detail, more sensitive to prompts v3.4 [2D,3D,Real,512~1088] ※include Fluffy Rock Quality Tags-LoRA stable version, more detail, clear result, reduce some noise (like bush,pattern) v3.5 [2D,3D,Real,512~1088] unstable version, contrast & detailed enhance v3.6 [2D,3D,Real,512~1088] stable version, more sensitive to e621 tags v3.7 [2D,3D,Real,512~1088] stable version, reduce noise overactivity, fix blurry eyes and finger error, fix failed background depth v4.0 [2D,3D,Real,512~1088] v-pred version, remix from accuracy anatomy and style with fewer prompt, little dim blue average color with smooth noise, weakly negative prompt issue v4.1 [2D,3D,Real,512~1088] v-pred version, color and low contrast fix, reduced realistic noise. v4.2 [2D,3D,Real,512~1088] v-pred version, more contrast and detail, yelow issue. if you feel too fried use =0.35 v4.3 [2D,3D,Real,512~1088] v-pred version, clear artist style, fix most yellow/brown issue the version doesn't need CFG Rescale v4.4 [2D,3D,Real,512~1088] v-pred version, no more yellow/brown issue. the version doesn't need CFG Rescale v5.0 [2D,3D,Real,896~1536] SDXL-lightning version, base on Compassmix XL. v5.1 [2D,3D,Real,896~1536] SDXL-lightning version, more e621 dataset, lower human face, better NSFW stuff. v5.2 [2D,3D,Real,896~1536] SDXL-lightning version, increase average quality. Little unstable than v51 but more creative. v6.0 [2D,3D,res:896~1536] More character better sex pose, limited and uncontrollable style (mostlly anime style). v6.1 [2D,3D,Real,896~1536] More realistic detail, reduce anime style, fix flat and boring background. v6.1a-RE [2D,3D,Real,896~1536] Same as v61 but adjust average style to simi-realistic. v6.2 [2D,3D,Real,896~1536] more effective prompt, keep style also with good realistic detail, saturation down little bit. v6.3 [2D,3D,Real,896~1536] Detail(noise) level between v62 and v61, upgrade character/artist accuracy. v6.4 [2D,3D,Real,896~1536] Upgrade light quality and average detail. Note about NoobXL to create stable furry (v6x): use "furry" tag in propmt can let AI create furry not human. use "no human" tag in propmt can avoid NoobXL model add human and reduce anthro affect (more original style). use "anime style" in negative propmt can reduce classic booru style and more realistic. Some SD prompt trick: Combine two character: characterA \(characterB\) Avoid tag bleeding: (chain:0)-link fence (cowboy:0) shot high (collar:0) Multi-tag combine, enhance and reduce token use: from side + side view = from side view crossed legs + legs up = crossed legs up Basic Style Negative Prompt SD1.5 unusual anatomy, mutilated, malformed, watermark, amputee, mosaic censorship, sketch, monochrome Negative Prompt SDXL malformed, worst quality, ba
8,654 stažení · 373 lajků na Civitai
SHA256
0FCBC5D18382CADCED30F0E7F097452AB6B09E66B42A0459646881D26D888B09
ID modelu ModelTrends.ai
#9315
Nahlásit obsah
Ukázkové rendery
Prompty a nastavení sdílená lidmi, kteří tyto rendery vytvořili na Civitai. Vyberte render a uvidíte, jak vznikl.
Nastavení
Sampler
DPM++ 2M Karras
Kroky
40
Guidance
7
Seed
2503393698
Velikost
640x896
Prompt
(by Wildering, by Oaks16, by Kenno Arkkan), young solo (nick wilde) grey shirt, jeans, purple stripes necktie, looking at viewer, (half-length portrait), blue eyes, hand on forehead, leaning forward on bar, bent over, three-quarter view, BREAK, colorful cityscape, abstract cityscape, plant, water, night, masterpiece, best quality, light, 4k, 2k, photography, photorealistic, analog style, realistic, photorealism
Negativní prompt
unusual anatomy, mutilated, malformed, watermark, amputee, mosaic censorship, sketch, monochrome
Nastavení
Sampler
DPM++ 2M Karras
Kroky
40
Guidance
7
Seed
2839048243
Velikost
640x896
Prompt
(by Victo Ngai, by Snowskau, by Victo Ngai), quadruped feral chibi (sky forme shaymin:1.25), white body, (green dipstick limbs), red scarf, round eyes, looking at viewer, three-quarter view, BREAK, colorful forest, abstract forest, plant, morning, masterpiece, best quality, light, 4k, 2k, photography
Negativní prompt
unusual anatomy, mutilated, malformed, watermark, amputee, mosaic censorship, sketch, monochrome
Nastavení
Sampler
DPM++ 2M Karras
Kroky
40
Guidance
7
Seed
3086791076
Velikost
640x896
Prompt
(by Kyoto Animation, by Christopher Balaskas, by Glacierclear, by Sususuigi), (duo toony chibi, frisk \(undertale\), asriel dreemurr, hug:1.25), shirt, pants, front view, (three-quarter portrait:1.25), arms above head, holding flower, happy, close-up, BREAK, colorful cave, colorful mountain, foggy, glowing, night, waterfall, crystal, plant, sky, masterpiece, best quality, light, 4k, 2k, photography
Negativní prompt
unusual anatomy, mutilated, malformed, watermark, amputee, mosaic censorship, sketch, monochrome
Nastavení
Sampler
Euler a
Kroky
15
Guidance
7
Seed
2606113583
Velikost
512x512
Prompt
cacturne, wide-brim hat, spines, large round eyes, sunken eyes, yellow eyes
Nastavení
Sampler
DPM++ 2M Karras
Kroky
40
Guidance
7
Seed
3987269271
Velikost
640x896
Prompt
(by Retros, by Liubov Sergeevna Popova, by Leonid Afremov), (toony clyde \(discord\):1.35), (white body, dot eyes:1.2, ori \(ori\):1.25), (half-length portrait, front view:1.2), cat ear, BREAK, abstract background, purple blue background, star-shaped background, masterpiece, best quality, light, 4k, 2k, photography
Negativní prompt
(hands on chest), mutilated, malformed, watermark, amputee, mosaic censorship
Nastavení
Sampler
DPM++ 2M Karras
Kroky
40
Guidance
7
Seed
1874988125
Velikost
640x896
Prompt
(by C-3Matome, by Wamudraws, by Waspsalad, by Waspsalad), chibi feral (duo charmander riolu:1.3), smile, yellow scarf, fanny pack, standing, pants, red eyes, (green eyes), (three-quarter portrait, three-quarter view:1.2), BREAK, (bubble, air bubble, bokeh:1.37), beach, sunset, night, cloud, foggy, masterpiece, best quality, light, 4k, 2k, photography
Negativní prompt
nipples, shota, size difference, mutilated, malformed, watermark, amputee, mosaic censorship
Nastavení
Sampler
DPM++ 2M Karras
Kroky
40
Guidance
7
Seed
1052375051
Velikost
640x896
Prompt
(by Youjomodoki, by Kiyosan, by Victo Ngai), chibi (quadruped feral vaporeon:1.3), (in water, leaning forward), (three-quarter view, half-length portrait:1.2), BREAK, (the backrooms, spa pool:1.35), (round swimming pool, arch window, corridor, white tile wall:1.25), pillar, depth of field, reflection floor, masterpiece, best quality, light, 4k, 2k, blender \(software\), ray tracing, 3d, unreal engine
Negativní prompt
(rear view, yellow room, yellow wall:1.25), mutilated, malformed, watermark, amputee, mosaic censorship, sketch, monochrome
Nastavení
Sampler
DPM++ 2M Karras
Kroky
40
Guidance
7
Seed
1810679854
Velikost
640x896
Prompt
(by Kemokin Mania, by Supplesee, by Deormynd), (quadruped feral doge:1.25), lying on front, black eyes, cross-eyed, (looking at away, three-quarter view, blep, bust portrait:1.25), foreground, depth of field, detailed background, BREAK, living room, white sofa, inside, plant, window, masterpiece, best quality, ultra realistic, 4k, 2k, (high detail:1.25), film photography, soft focus, RAW photo, photorealistic, analog style, subsurface scattering, photorealism
Negativní prompt
unusual anatomy, mutilated, malformed, watermark, amputee, mosaic censorship
AI modely pro generování obrázků, videa a textu
yiffymix42 je základní model pro rodinu Stable Diffusion 1.5 uvedený na ModelTrends.ai, katalogu open source AI modelů pro obrázky, video a text určeném jen ke čtení. Porovnejte ho s dalšími modely Stable Diffusion 1.5, podívejte se na jeho skóre žhavosti a vyzkoušejte ho na PirateDiffusion nebo BitVector.
Procházet podle rodiny modelů
Procházet všechny modely