first-person-camera-perspective/info.txt

═══════════════════════════════════════════════════════════════════════════════
  FIRST-PERSON CAMERA PERSPECTIVE
═══════════════════════════════════════════════════════════════════════════════

───────────────────────────────────────────────────────────────────────────────
  IDENTITY
───────────────────────────────────────────────────────────────────────────────
  Base model        Krea 2
  Generation mode   not declared by the author
  Checkpoint        not determined — verify before use
  Category          Character / subject
  Author            oreolove
  Source            https://civitai.com/models/2814043
  Provenance        CivitAI · model 2814043 · version 3180152

───────────────────────────────────────────────────────────────────────────────
  WEIGHTS
───────────────────────────────────────────────────────────────────────────────
  File              第一人称摄像.safetensors
  Version           v2.0
  Size              218.0 MB
  Format            SafeTensor / unknown precision
  SHA256            2a1cfe6bb47aab120048da39bcc6e994d8aaae1fa65e6afcd884d97ecb08bc10
  Published         2026-07-30

───────────────────────────────────────────────────────────────────────────────
  TRIGGER WORDS
───────────────────────────────────────────────────────────────────────────────
  › "true first-person body POV"

───────────────────────────────────────────────────────────────────────────────
  RECOMMENDED SETTINGS
───────────────────────────────────────────────────────────────────────────────
  Taken verbatim from the author's description:

  LoRA strength       0.7–1.0

───────────────────────────────────────────────────────────────────────────────
  ADOPTION & POPULARITY
───────────────────────────────────────────────────────────────────────────────
  Downloads               2,203
  Rating                  100% positive (115/115)
  Comments                0
  Published               37 days ago
  Download rate           42.7/day since release

  Adoption rank           #109 of 200 in this collection  (Modest)
  Momentum rank           #87 of 200 by download rate  (Steady · fresh release)

  Adoption tier is the percentile of total downloads within this collection;
  momentum is the percentile of downloads-per-day since release. Momentum is
  ranked rather than measured against a fixed rate, because this base model
  is itself new and every LoRA looks fast on an absolute scale. Both numbers
  are CivitAI's, read on the scrape date at the foot of this file.

───────────────────────────────────────────────────────────────────────────────
  CHAINING / STACKING
───────────────────────────────────────────────────────────────────────────────
  Stacks with others      not stated

  The author gave no chaining guidance. The rules below are the
  general Krea 2 ones, not anything specific to this LoRA.

  General Krea 2 rules that apply here (see REFERENCE.txt):

  • The most important rule is not about chaining but about which
    checkpoint you chain onto: the official README says in bold "TRAIN on
    Raw and RUN on Turbo", and "We highly recommend using RAW for training
    LoRAs and applying them on Turbo for inference." LoRAs trained on Raw
    are stated to work well on Turbo.
  • Chain with LoraLoaderModelOnly nodes in series (model -> model). Krea 2
    LoRAs are DiT-only, so there is no CLIP side to chain and the text-
    encoder branch stays untouched however many LoRAs you add.
  • Krea 2 LoRAs stack in practice and the community treats multi-LoRA as
    routine - style + character, style + slider, realism + character.
    Several CivitAI Krea 2 authors state their LoRAs stack cleanly; one
    writes "I recently stacked over 20 of my own LoRAs on a single
    generation and the output still came out great."
  • Reduce per-LoRA strength when stacking. CivitAI Krea 2 authors converge
    on dropping from ~1.0 to roughly 0.6-0.9 once more than one adapter is
    loaded. The CivitAI 12GB training guide also notes rank affects
    composability: "rank 8 produced a lighter style influence that was
    easier to stack with other LoRAs, rank 16 provided a useful balance
    between concept strength and composability, and rank 32 was better
    suited to a precise object or concept intended to take priority over
    other stacked LoRAs."
  • Accelerator LoRAs are position-sensitive in intent, not in node order:
    a Raw-to-Turbo delta adapter belongs on the Raw checkpoint, a
    sub-8-step LoRA belongs on Turbo (or on Raw already carrying a Raw-to-
    Turbo adapter). Chaining Raw -> Raw-to-Turbo adapter -> 4-step LoRA is
    explicitly recommended by the 4-step LoRA's author.
  • Whatever you stack, the schedule must stay Turbo's: cfg 1.0 in ComfyUI
    (guidance 0.0 in diffusers) and mu/shift 1.15. The 4-step LoRA's card
    says "Keep mu = 1.15. The training targets are anchored to that grid; a
    different shift moves the [sampler off them]"; the same reasoning
    applies to any Turbo-trained adapter in the chain.
  • Reference/edit LoRAs are designed to be stacked under ordinary subject
    and style LoRAs - the Identity Edit card states "Composes with your
    LoRAs: character/body/style LoRAs stack on top and steer the prior" and
    recommends a stacked subject LoRA when unusual subjects drift toward
    the base prior.
  • Krea 2 LoRAs cannot be chained with LoRAs for any other base model.
    Many CivitAI pages carry multi-model titles like "(Krea-2 + ZIT)" or
    "[Flux | ZIB | Krea2]" - those are separate files for separate
    architectures shipped under one model page, not a combined adapter.
  • To combine two full Krea 2 checkpoints rather than adapters, ComfyUI
    ships a dedicated ModelMergeKrea2 node (added in v0.27.0) with per-
    section weights for first., tmlp., txtmlp., tproj.,
    txtfusion.projector, txtfusion.layerwise_blocks.0-1,
    txtfusion.refiner_blocks.0-1, blocks.0-27 and last.
  • The author never states which weight family this targets. Silent
    degradation, never a hard error, between Raw and Turbo. The two share
    one architecture - ai-toolkit's config is commented "The reference
    'single_mmdit_large_wide' architecture (oss_raw / oss_turbo share it)"
    - so every LoRA tensor shape matches on both and ComfyUI/diffuser

───────────────────────────────────────────────────────────────────────────────
  PROS
───────────────────────────────────────────────────────────────────────────────
  + Well established — 2,203 downloads. [source: CivitAI stats]
  + Positively received — 115 thumbs-up with no down-votes. [source:
    CivitAI stats]
  + Explicit trigger word(s) — true first-person body POV — so the effect
    can be turned on and off from the prompt. [source: model metadata]
  + Compact at 218 MB — cheap to stack with other LoRAs. [source: file
    size]
  + Author published concrete recommended settings. [source: description]

───────────────────────────────────────────────────────────────────────────────
  CONS & CAVEATS
───────────────────────────────────────────────────────────────────────────────
  - Author references NSFW output — review before using in shared work.
    [source: description]
  - Author never states which generation mode it was trained for; test
    against your own workflow before relying on it. [source: description]

───────────────────────────────────────────────────────────────────────────────
  COMPATIBILITY WARNING
───────────────────────────────────────────────────────────────────────────────
  Silent degradation, never a hard error, between Raw and Turbo. The two
  share one architecture - ai-toolkit's config is commented "The reference
  'single_mmdit_large_wide' architecture (oss_raw / oss_turbo share it)" - so
  every LoRA tensor shape matches on both and ComfyUI/diffusers will load an
  adapter against either without complaint. The lvladikov 4-step LoRA card
  states this for the reverse direction: "Every layer it targets also exists
  in Krea 2 Raw, so it will load there without complaint - but that is a side
  effect of the shared architecture, not a supported mode", and reports
  mixed, subject-dependent results with malformed subjects (duplicated heads,
  fused limbs) at low step counts, needing 14+ steps with Raw's CFG on before
  output is coherent. The intended direction (train on Raw, run on Turbo) is
  officially blessed. The more common practical failure is a settings
  mismatch rather than a weight mismatch: running a Turbo-targeted LoRA at
  Raw's 52 steps + CFG 3.5, or leaving CFG enabled on Turbo, degrades output
  with no warning. Loading a Krea 2 LoRA against a different model family
  entirely (Flux, Qwen-Image, Z-Image) is also not an error - ComfyUI logs
  "lora key not loaded: {key}" per key and generates as if no LoRA were
  applied.

───────────────────────────────────────────────────────────────────────────────
  AUTHOR'S DESCRIPTION
───────────────────────────────────────────────────────────────────────────────
  True First-Person Female Body POV 这是一个专注于 真实女性第一人称身体视角 的 LoRA。
  相机位于成年女性角色的眼睛位置，向下能够看到属于视角主体自己的手臂、身体、衣物、腿和脚，而不是第三人称俯拍、自拍或普通的“POV风格”构图。
  V2.0 更新说明 V2.0 进一步强化真实的第一人称身体视角，改善双手、手臂、躯干和双腿从画面下方自然延伸的效果。提升行走、坐姿、日常动作、人物互动
  及复杂场景的稳定性，并减少第三人称跟拍、后脑勺、漂浮肢体和身体缺失等问题。
  核心提示词：
  true first-person body POV 按需添加：
  adult female viewpoint
  adult male viewpoint
  Recommended Settings - LoRA weight：建议从 0.7–2.0

  - CFG、采样器和步数：根据底模调整

  - 支持竖图与横图

  - 竖图更适合表现完整身体、腿部和脚部

  - 横图更适合双人互动、多人场景和环境构图

  如果第一人称效果不够明显，可以增加：
  looking down at her own body, her own hands visible, her own torso visible,
  her own legs visible 如果出现第三人称镜头，可以尝试加入负面提示词：
  third-person view, external camera, overhead camera, selfie, mirror selfie,
  full character seen from outside, detached hands, extra arms, extra legs
  Example Prompts 日常场景 true first-person body POV, adult female viewpoint,
  looking down at her own clothed body, cardigan, jeans, hands resting on her
  lap, sitting at a cafe, warm window light, photorealistic 户外场景 true first-
  person body POV, adult female viewpoint, walking on a forest trail, her own
  hands, jacket, trousers and hiking boots visible, mountains in the
  distance, natural daylight, photorealistic 双人互动 true first-person body POV,
  adult female viewpoint, holding hands with an adult partner, her own arm,
  clothes, legs and shoes visible, walking through a city at night,
  affectionate atmosphere, photorealistic 多人场景 true first-person body POV,
  adult female viewpoint, sitting with a diverse group of adult friends, her
  own hands and lap visible, friends interacting naturally, rooftop lounge,
  cinematic lighting, photorealistic Training Dataset 本 LoRA 使用了 80
  组图文配对进行训练，训练集包含：
  - 单人、双人和多人构图

  - 站立、坐姿、行走、运动和日常动作

  - 拥抱、依偎、牵手、慢舞等亲密但非露骨的互动

  - 咖啡馆、家庭、户外、旅行、工作坊和社交活动

  - 酒吧、爵士酒廊、夜店、赌场、屋顶酒廊和晚宴等成人社交场所

  - 38 张竖图和 42 张横图

  - 多种分辨率与画面比例

  - 东亚、南亚、黑人、拉丁裔、中东、混血及多族裔成年人

  训练数据均为 明确成年人、完整着装、非露骨内容 。
  Notes - LoRA 的核心能力是第一人称身体构图，不是固定人物或固定服装。

  - 人物族裔、肤色、体型、服装和场景可以通过提示词单独控制。

  - 复杂的双手动作、镜面反射和多人肢体接触仍可能受到底模能力影响。

  - 权重过高可能产生夸张的向下视角、重复肢体或身体比例问题。

  - 本模型没有使用裸体或性行为图片训练，因此不能保证 NSFW 构图的稳定性。

  - 请仅用于明确的成年角色。

  English Description True First-Person Female Body POV This LoRA is designed
  to create a genuine first-person body perspective from the viewpoint of an
  adult woman .
  The camera is positioned at the character’s eye level, looking down at her
  own arms, hands, clothing, torso, legs, or feet. It is intended to avoid
  third-person overhead shots, selfies, and images that merely resemble a POV
  composition.
  Trigger Words true first-person body POV, adult female viewpoint Place the
  trigger phrase near the beginning of your prompt.
  Suggested Weight 0.7–1.0 Start lower and increase the weight if the first-
  person body perspective is not strong enough.
  Helpful supporting phrases:
  looking down at her own body, her own hands visible, her own torso visible,
  her own legs visible Suggested negative prompt:
  third-person view, external camera, overhead camera, selfie, mirror selfie,
  full character seen from outside, detached hands, extra arms, extra legs
  Dataset The LoRA was trained on 80 image-caption pairs featuring:
  - Solo, couple and group compositions

  - Sitting, standing, walking, sports and everyday activities

  - Hand-holding, embraces, cuddling and slow dancing

  - Indoor, outdoor, travel and social environments

  - Adult nightlife venues such as cocktail bars, lounges, clubs, casinos and
  evening events

  - 38 portrait and 42 landscape images

  - Multiple resolutions and aspect ratios

  - Diverse adult subjects, including East Asian, South Asian, Black, Latina,
  Middle Eastern and mixed-race representation

  All training subjects are clearly adults. The training dataset is fully
  clothed and non-explicit.
  Important Notes This LoRA focuses on perspective rather than a specific
  character, ethnicity, body type, outfit or location. These details should
  be controlled through your prompt.
  Very complex hand interactions, mirrors and crowded scenes may still depend
  heavily on the capabilities of the base model. Excessively high LoRA
  strength may produce distorted limbs or an exaggerated downward camera
  angle.

───────────────────────────────────────────────────────────────────────────────
  VERSION NOTES
───────────────────────────────────────────────────────────────────────────────
  V2.0 进一步强化真实的成年女性第一人称身体视角，改善双手、手臂、躯干和双腿从画面下方自然延伸的效果。提升行走、坐姿、日常动作、双人互动以及室内外复
  杂场景的稳定性，减少第三人称跟拍、后脑勺和身体缺失等问题，同时兼容日常与 NSFW 构图。

───────────────────────────────────────────────────────────────────────────────
  EXAMPLE MEDIA
───────────────────────────────────────────────────────────────────────────────
  6 preview(s) in ./example_images/ — community results for
  this LoRA. Videos keep a matching _poster.jpg still frame.

  No prompts are recorded below: CivitAI's public API flags these posts as
  having generation metadata but does not return it, so the prompts cannot be
  scraped. Open the model page to read them.

  01_image.jpeg  (image, 1024x1536)
  02_image.jpeg  (image, 1080x1920)
  03_image.jpeg  (image, 1080x1920)
  04_image.jpeg  (image, 1080x1920)
  05_image.jpeg  (image, 1080x1920)
  06_image.jpeg  (image, 1080x1920)

───────────────────────────────────────────────────────────────────────────────
  HOW TO USE (COMFYUI)
───────────────────────────────────────────────────────────────────────────────
  1. Update ComfyUI to at least v0.26.0 (released 2026-06-23), which added
  local Krea2 support. For reference-image / style-reference / edit LoRAs you
  need at least v0.29.0 (2026-07-29), which added regular and timestep-zero
  reference images for Krea 2. ModelMergeKrea2 arrived in v0.27.0
  (2026-06-30).

  2. Put the base stack in place (files from huggingface.co/Comfy-Org/Krea-2,
  which is not gated):
     - ComfyUI/models/diffusion_models/krea2_turbo_fp8_scaled.safetensors
  (documented recommended default; the repo also holds krea2_turbo_bf16,
  _int8_convrot, _mxfp8, _nvfp4 and krea2_raw_bf16 / _fp8_scaled /
  _int8_convrot)
     - ComfyUI/models/text_encoders/qwen3vl_4b_fp8_scaled.safetensors (bf16
  also available)
     - ComfyUI/models/vae/qwen_image_vae.safetensors

  3. Put the LoRA .safetensors in ComfyUI/models/loras/ - flat, no per-model
  subfolder required.

  4. Build or load the graph. The official image_krea2_turbo_t2i.json
  template is: UNETLoader (krea2_turbo_fp8_scaled.safetensors) ->
  LoraLoaderModelOnly -> KSampler; CLIPLoader
  (qwen3vl_4b_fp8_scaled.safetensors, type "krea2") -> text encode ->
  KSampler positive, with ConditioningZeroOut into negative; VAELoader
  (qwen_image_vae.safetensors) -> VAEDecode -> SaveImage; EmptyLatentImage
  1024x1024 driven by ResolutionSelector. An int8 sibling template
  (image_krea2_turbo_t2i_int8.json) also ships.

  5. Load the LoRA with LoraLoaderModelOnly, not LoraLoader - both official
  templates do. Krea 2 LoRAs patch the DiT only; note that the DiT's own
  text_fusion / txtfusion blocks are a normal LoRA target (the official style
  LoRAs patch them), but the Qwen3-VL text encoder itself is not. Set
  strength 1.0 for Krea's official style LoRAs (the shipped template uses
  0.8) and add the LoRA's trigger word to the prompt.

  6. Sampler settings: steps 8, cfg 1, sampler euler, scheduler simple,
  denoise 1.0. Do not add a ModelSampling node for plain t2i - ComfyUI
  already applies shift 1.15 from Krea2.sampling_settings.

  7. For style reference, use the dedicated template: UNETLoader
  krea2_turbo_int8_convrot.safetensors, LoraLoaderModelOnly
  krea2_style_reference.safetensors at 1.0, ModelSamplingFlux (1.15, 0.5),
  TextEncodeQwenImageEditPlus fed by LoadImage,
  FluxKontextMultiReferenceLatentMethod set to index_timestep_zero, and
  SamplerCustomAdvanced with KSamplerSelect euler + BasicScheduler simple/8 +
  CFGGuider cfg 1.

  8. For instruction editing (Krea 2 Identity Edit), stock nodes are not
  enough: install the ComfyUI-Krea2Edit node pack, which ships its own
  workflows, and run Turbo at 8-12 steps / cfg 1 (or Raw at 20 steps / cfg 3
  for removals) with LoRA strength 1.0.

  9. Low-VRAM alternative: install city96's ComfyUI-GGUF and use a community
  GGUF build (realrebelai/KREA-2_GGUFs, quantized from Turbo;
  molbal/krea2-gguf, quantized from Raw) with the Unet Loader (GGUF) node in
  place of UNETLoader. There is no official GGUF release. LoRA loading is
  unchanged.

───────────────────────────────────────────────────────────────────────────────
  Scraped by lorakit on 2026-09-05 03:54 UTC.
  Stats and description are the author's; pros/cons are derived from the
  evidence tagged beside each line.
───────────────────────────────────────────────────────────────────────────────