Model
Trends
.ai
Model
Trends
.ai
les meilleurs modèles d'IA open source
Exécuter en local
Turbo-ANIMA-v4.safetensors
267 MB · SafeTensor · bf16
Les téléchargements sont servis par Civitai. Certains créateurs demandent d'abord une connexion à Civitai.
AD
<turbolora-anima>
À propos de ce modèle
ANIMA · LoRA
Créé par
n_Arno
sur Civitai
by n_Arno - TURBO for ANIMA (less steps)
Notes du créateur
TL;DR: This is a DMD2 LoRA = use CFG 1 and 8-12 steps (even if i personally prefer 16 steps, that's still half of what i usually use and i get my pictures in 30s instead of 80s). Versions Comparison (V1 to V4, 8, 12 and 16 steps): - No other LoRA: - With a character LoRA: - With a style LoRA: CFG vs LoRA strength (V4, 12 Steps): Quick clarification: - V1 is using turbo 0.1 - V2 is using turbo 0.2 - V1.5 is using a merge of 0.1 and 0.2 - V3 is based on anima-turbo-v1.0 - V2.9 is based on anima-turbo-v1.0 and turbo 0.2 - V4 is based on anima-turbo-v1.1 - All of them has been merged with the revised cosmos2.5 DMD2 LoRA - Yes, you can use CFG 1.2, 1.4, etc... you may need to add more steps then (that's why i do 16). V4! By popular request, this version is based on my own extract of anima-turbo-v1.1 (128/64) + the cosmos LoRA (ratio 0.65/0.35) and resized to 64/32. PS: V4 has been re-uploaded: i removed the diff layers because ComfyUI don't like those with ANIMA. Correct sha256sum is aa198376f2f31159ba3f60dce19924b27411cdd93e7252543e5c45249ca89048 V2.9 With more extensive tests and help from heavy user of the previous version, it was clear that V3 was killing LoRA when used. So, here is V2.9, a step back to previous turbo for the sake of a better compatibility with LoRA. Recipe (merge done at Rank 128/64): - Cosmos2.5 DMD2 LoRA: 0.3 - Extract Turbo V1.0 LoRA: 0.2 - Turbo v0.2 LoRA: 0.4 Then, all this went through my (MAXDIM 64, CUTOFF 98) to get this slightly heavier LoRA, but providing from my first tests better results. 🥰 V3 With officially out, i knew some people would ask about an update. So here it is! I switched my approach here as this is a full model we are talking about. First, i merged base and turbo at 50/50 to get "half-turbo" in which i merged the Cosmos2 LoRA at 0.5 to get "custom-turbo". V3 is a LoRA extraction of "custom-turbo" minus "base". V1.5 Borrowing a book from and for the people not satisfied by 0.1 and 0.2 and wanted something in the middle, i did a merge of official 0.1 and 0.2 before doing the merge with the cosmos2.5 distilled LoRA. This end being a version between V1 and V2 = V1.5. This will probably be the last version except if a 0.3 version of the official LoRA comes out (and/or if a full distilled version of ANIMA base is released). NB: this version feels more sensitive to watermarks, you can use CFG 1.2-1.4 to be able to add a negative. V2 By popular demand, here is a V2 of this LoRA based on the V0.2 of the source turbo LoRA. 😘 V1 This is my "personal" brand of the classic ANIMA Turbo LoRA, based on the method. There is already several "Turbo" LORA for ANIMA: - - But interesting enough, had the idea to make and test a LoRA using the original Cosmos-Predict2.5 architecture: The main process was: extract (using SVD) a LoRA out of "" minus "" and test it on ANIMA... and it works! (even if some keys are refused because they changed shape in ANIMA). Below is a comparaison of what those bring to the table (RDBT is very close to the base Turbo and so was excluded). Now, what is did is "stupid" = Merge those two 😁 (i left RDBT alone as sharing merge is forbidden). To do so, i re-keyed both LoRA and do a re-rank of the resulting merge (32/16 instead of 64/64+32/32). The ratio was 6/4. This way, i get more details but with a less saturated result. And it works perfectly with : Thanks for reading! 💖 Legal The CircleStone Model is licensed by CircleStone Labs LLC under the CircleStone Non-Commercial License. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
2,616 téléchargements · 206 j'aime sur Civitai
SHA256
AA198376F2F31159BA3F60DCE19924B27411CDD93E7252543E5C45249CA89048
ID de modèle ModelTrends.ai
#23608
Signaler le contenu
Rendus d'exemple
Prompts et réglages partagés par les personnes qui ont réalisé ces rendus sur Civitai. Choisissez un rendu pour voir comment il a été fait.
Réglages
Sampler
euler_ancestral
Étapes
9
Guidance
1
Seed
2140704112
Taille
832x1216
Poids utilisé
1
Prompt
masterpiece, best quality, score_9, score_8_up, 1girl, solo, Sumin, stunning, 20 years adult Korean female, soft smoky eyes and glossy berry lips, brown eyes, soft chestnut long straight hair, pale pink sleeveless blouse, white short pleated skirt, heels, bright spring afternoon in a flower garden, clear weather, colorful blooms all around, standing on a garden path, lightly holding the hem of her skirt, looking at viewer with a warm feminine smile, Enchanting Eyes
Prompt négatif
low quality, worst quality, bad anatomy, bad hands, extra fingers, missing fingers, extra limbs, malformed face, distorted eyes, asymmetrical eyes, blurry, overexposed skin, washed out colors, text, watermark, logo, jpeg artifacts, censored
Réglages
Sampler
euler_ancestral
Étapes
9
Guidance
1
Seed
229307365
Taille
832x1216
Poids utilisé
1
Prompt
masterpiece, best quality, score_9, score_8_up, 1girl, solo, Sumin, stunning, 20 years adult sexy Korean female, soft smoky eyes and glossy berry lips, sleek short black bob with a side part, small silver earrings, fitted sleeveless white top, high-waisted black pencil skirt, heels, standing inside a spacious contemporary art gallery, one hand loosely holding a folded exhibition brochure while she turns toward viewer, relaxed posture, subtle amused smile, large abstract paintings and polished gallery floor behind her, refined quiet date atmosphere, Enchanting Eyes,
Prompt négatif
low quality, worst quality, bad anatomy, bad hands, extra fingers, missing fingers, extra limbs, deformed body, malformed face, distorted eyes, asymmetrical eyes, blurry, overexposed skin, washed out colors, text, watermark, logo, jpeg artifacts, censored
Réglages
Sampler
euler_ancestral
Étapes
9
Guidance
1
Seed
1390976276
Taille
832x1216
Poids utilisé
1
Prompt
masterpiece, best quality, score_9, score_8_up, 1girl, solo, Sumin, stunning, 20 years adult Korean female, soft smoky eyes and glossy berry lips, Perfect body proportions, detailed eyes, brown eyes, sleek short black bob with a side part, small silver earrings, fitted sleeveless white top, high-waisted black pencil skirt, heels, standing inside a spacious contemporary art gallery, one hand loosely holding a folded exhibition brochure while she turns toward viewer, relaxed posture, subtle amused smile, large abstract paintings and polished gallery floor behind her, refined quiet date atmosphere, Enchanting Eyes,
Prompt négatif
low quality, worst quality, bad anatomy, bad hands, extra fingers, missing fingers, extra limbs, deformed body, malformed face, distorted eyes, asymmetrical eyes, blurry, overexposed skin, washed out colors, text, watermark, logo, jpeg artifacts, censored
Réglages
Sampler
er_sde
Étapes
25
Guidance
5
Seed
1566543253
Taille
832x1216
Poids utilisé
1
Prompt
Masterpiece,very aesthetic, best quality, score_9, detailed, highres, masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest, print quality, award winning, dramatic composition, 1boy, solo, blonde hair, medium hair, orange eyes, scowl, sneakers, dress, plaid, hand on hip, dungeon, theater stage, twilight, dry air, high contrast, sidelighting, three-quarter view, full body, tilt-shift lens, motion picture film, camera shake, ink wash, halftone, visual novel, autumn leaves. high dynamic range, background blur, cinematic, key visual, silhouette ,scnr, dynamic lighting ,depth of field, Technicolor, Panavision, realistic skin, detailed face, detailed eyes, detailed hair, detailed head visor, clean composition,@gpt-image-2,
Prompt négatif
worst quality, low quality, score_1, score_2, score_3, bystander, bad anatomy, blurry eyes, extra fingers, fused fingers, loli, child, text, signature, logo, anime,
Réglages
Sampler
Euler a
Étapes
12
Guidance
1
Seed
213325134112650
Taille
1024x1536
Prompt
@bl00dlust, score_7, score_8, score_9, fine art parody, ornate border, detailed background, slightly cracked, 1girl, smile, very long hair, wavy hair, golden hair, golden eyes, dark green witch hat with gold trim, dark green pauldrons with gold trim, dark green vambraces with gold trim, large breasts, cleavage, dark green shrug, long sleeves, fingerless gloves, holding tall wooden staff, wizard staff, dark green pleated skirt, sun with face, sun in splendor, sunflower ornament on hat,
Prompt négatif
score_1, score_2, score_3, lowres, extra digit, fewer digits, worst quality, jpeg artifacts, signature, watermark, artist name, bad perspective, artistic error, bad proportions, disfigured, deformed body, malformed limbs, flat color, outline, text, lips,
Réglages
Sampler
Euler a
Étapes
12
Guidance
1
Seed
901772703689140
Taille
1024x1536
Prompt
@bl00dlust, score_7, score_8, score_9, fine art parody, ornate border, detailed background, slightly cracked, ho'olheyak \(arknights\), 1girl, solo, grey hair, short hair, head wings, aqua eyes, gradient feathers, hand on own chin, evil smile, fangs, looking at viewer, jellyfish cut, juliet sleeves, ribbed dress, medium breasts, traditional dress, black dress with copper verdigris trim, perky breasts, taut clothes,
Prompt négatif
hood, score_1, score_2, score_3, lowres, extra digit, fewer digits, worst quality, jpeg artifacts, signature, watermark, artist name, bad perspective, artistic error, bad proportions, disfigured, deformed body, malformed limbs, flat color, outline, text, lips,
Réglages
Sampler
Euler a
Étapes
12
Guidance
1
Seed
1004499146416692
Taille
1024x1536
Prompt
@bl00dlust, score_7, score_8, score_9, fine art parody, ornate border, detailed background, slightly cracked, (vine border, leaf border:1.4), bunches of purple grapes on green vines, takagaki kaede, 1girl, smile, gesture, holding bunch of purple grapes, short hair, dark green hair, heterochromia, green-blue eye, blue-green eye, mole under eye, dark green dress with gold trim, juliet sleeves, medium breasts, perky breasts,
Prompt négatif
score_1, score_2, score_3, lowres, extra digit, fewer digits, worst quality, jpeg artifacts, signature, watermark, artist name, bad perspective, artistic error, bad proportions, disfigured, deformed body, malformed limbs, flat color, outline, text, lips,
Réglages
Sampler
Euler a
Étapes
32
Guidance
4
Seed
472237685276539
Taille
1024x1536
Prompt
@bl00dlust, score_7, score_8, score_9, fine art parody, detailed background, slightly cracked, sephiroth, fire, mansion on fire, 1boy, male focus, manly male, solo, grey hair, long hair, long bangs, aqua eyes, looking at viewer, curtained hair, pauldrons, black jacket, open jacket, cross straps over chest, expressionless,
Prompt négatif
score_1, score_2, score_3, lowres, extra digit, fewer digits, worst quality, jpeg artifacts, signature, watermark, artist name, bad perspective, artistic error, bad proportions, disfigured, deformed body, malformed limbs, flat color, outline, text, lips,
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.
turbolora on ModelTrends.ai: #20 of 366 Anima models
turbolora on ModelTrends.ai: #20 of 353 Anima LoRAs
Modèles d'IA pour générer image, vidéo et texte
turbolora anima est un LoRA pour la famille Anima, référencé sur ModelTrends.ai, un catalogue en lecture seule de modèles d'IA open source pour l'image, la vidéo et le texte. Comparez-le aux autres modèles Anima, consultez son score de chaleur pour suivre sa tendance et ouvrez-le sur PirateDiffusion ou BitVector pour l'essayer.
Parcourir par famille de modèles
Voir tous les modèles