Alex995647

Add 20 LoRA(s): qwen-image-edit-2511-lightning-4steps-v1-0-bf16-safetensors, mcsc-minecraft-skin-creator, qwen-anime-illustration-style, qwen-lightning-lora…

6eaeb7b verified 2 months ago

Raw History Blame Contribute Delete

16.8 kB

═══════════════════════════════════════════════════════════════════════════════
  QWEN LIGHTNING LORA
═══════════════════════════════════════════════════════════════════════════════

───────────────────────────────────────────────────────────────────────────────
  IDENTITY
───────────────────────────────────────────────────────────────────────────────
  Base model        Qwen-Image
  Generation mode   not declared by the author
  Checkpoint        not determined — verify before use
  Category          Speed / step-reduction
  Author            darksidewalker
  Source            https://civarchive.com/models/1854805?modelVersionId=2235536
  Provenance        CivitAI · model 1854805 · version 2235536

───────────────────────────────────────────────────────────────────────────────
  WEIGHTS
───────────────────────────────────────────────────────────────────────────────
  File              Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors
  Version           Qwen-2.0-bf16-8-Step
  Size              810.2 MB
  Format            SafeTensor / unknown precision
  SHA256            5bdbf69912280a9944be9b3aacd8db0cfbb429fcbd66c994d7b38b5a37e357ee
  Published         2025-09-20

───────────────────────────────────────────────────────────────────────────────
  TRIGGER WORDS
───────────────────────────────────────────────────────────────────────────────
  No trigger word. The LoRA applies as soon as it is loaded —
  strength is the only way to dial the effect up or down.

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

  LoRA strength       1.0
  Sampler steps       8
  CFG / guidance      1

───────────────────────────────────────────────────────────────────────────────
  ADOPTION & POPULARITY
───────────────────────────────────────────────────────────────────────────────
  Downloads               8,785
  Rating                  no votes yet
  Comments                32
  Published               353 days ago
  Download rate           24.9/day since release

  Adoption rank           #36 of 200 in this collection  (High)
  Momentum rank           #11 of 200 by download rate  (Hot)

  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 Qwen-Image ones, not anything specific to this LoRA.

  General Qwen-Image rules that apply here (see REFERENCE.txt):

  • Stack by wiring LoraLoaderModelOnly nodes in series on the MODEL line.
    This is the officially shipped pattern:
    template_qwen_Image_2512_360_lora chains Qwen-
    Image-2512-Lightning-4steps-V1.0-fp32 at 1.0 into
    qwen-360-diffusion-2512-int8-bf16-v2 at 1.0.
  • One accelerator LoRA maximum. Every official template loads exactly one
    Lightning/Turbo LoRA, and ComfyUI's Qwen-Image docs record that the
    fully-distilled checkpoint and the lightx2v 8-step LoRA are not usable
    together.
  • Match the accelerator to the checkpoint family: Qwen-
    Image-2512-Lightning on 2512, Qwen-Image-Lightning on the August base,
    the Edit-2509 subfolder LoRAs on Edit-2509, Qwen-Image-
    Edit-2511-Lightning on Edit-2511. lightx2v distilled and shipped these
    separately per family.
  • When any accelerator LoRA is in the chain, move the sampler to that
    LoRA's step count and cfg 1.0. Leaving cfg at 4.0 with a distilled LoRA
    is the most common bad-output cause.
  • Order used by the official templates: accelerator LoRA adjacent to the
    base loader, concept/style LoRA after it, then ModelSamplingAuraFlow,
    then the sampler (the 360-panorama template's exact order).
  • Keep the summed strength of concept/style LoRAs roughly in the 0.9-1.2
    band (CivitAI article 18798). The accelerator LoRA sits outside that
    budget at its own 1.0.
  • Control LoRAs (qwen_image_union_diffsynth_lora.safetensors) chain like
    ordinary LoRAs and combine with an accelerator: the official 'Qwen-
    Image Union Control' template stacks the control LoRA with Qwen-Image-
    Lightning-4steps-V1.0, both at 1.0, sampling at 4 steps / cfg 1.0 /
    shift 3.1.
  • Be conservative stacking older Edit LoRAs on Edit-2511: the Qwen README
    says community LoRA effects were merged into the 2511 base, so those
    LoRAs can double-apply.
  • The dominant family is Qwen-Image-Lightning by lightx2v / ModelTC
    (github.com/ModelTC/Qwen-Image-Lightning), CFG-distilled LoRAs released
    per checkpoint family. 2512 Lightning files are 0.85 GB in bf16 and
    1.70 GB in fp32 - high-rank LoRAs, not small ones. Repo layout
    (verified against the HF file listings): lightx2v/Qwen-Image-Lightning
    holds the T2I LoRAs (4steps-V1.0, 4steps-V2.0, 8steps-V1.0,
    8steps-V1.1, 8steps-V2.0, each also in -bf16), a Qwen-Image-fp8-e4m3fn-
    Lightning-4steps-V1.0 distilled against the naive fp8 base, the
    original Qwen-Image-Edit Lightning 4/8-step files, an Edit-2509 s
  • The author never states which weight family this targets. Mismatch is
    silent degradation, essentially never a hard error. Every Qwen-Image
    weight family resolves to the same ComfyUI model class
    (comfy.model_base.QwenImage, unet_config image_model "qwen_image",
    latent_format Wan21, built-in sampling shift 1.15 -
    comfy/supported_models.py

───────────────────────────────────────────────────────────────────────────────
  PROS
───────────────────────────────────────────────────────────────────────────────
  + Widely adopted — 8,785 downloads. [source: CivitAI stats]
  + Author published concrete recommended settings. [source: description]

───────────────────────────────────────────────────────────────────────────────
  CONS & CAVEATS
───────────────────────────────────────────────────────────────────────────────
  - No trigger word — the LoRA is always on once loaded, so strength is the
    only control. [source: model metadata]
  - Author never states which generation mode it was trained for; test
    against your own workflow before relying on it. [source: description]
  - Large at 810 MB — slower to load and heavier to stack. [source: file
    size]

───────────────────────────────────────────────────────────────────────────────
  COMPATIBILITY WARNING
───────────────────────────────────────────────────────────────────────────────
  Mismatch is silent degradation, essentially never a hard error. Every Qwen-
  Image weight family resolves to the same ComfyUI model class
  (comfy.model_base.QwenImage, unet_config image_model "qwen_image",
  latent_format Wan21, built-in sampling shift 1.15 -
  comfy/supported_models.py), and the bf16/fp8 file sizes are identical
  across Qwen-Image, Qwen-Image-2512, Qwen-Image-Edit, Edit-2509 and
  Edit-2511. So a LoRA trained on any of them will key-match and load against
  any other. Where keys genuinely do not match, ComfyUI only logs `lora key
  not loaded: <key>` (comfy/lora.py:93) and continues; a shape mismatch logs
  `WARNING SHAPE MISMATCH <key> WEIGHT NOT MERGED` (comfy/lora.py:498) and
  skips that tensor. Both are console warnings; the render still completes.
  Verified consequence: lightx2v re-distilled and re-released Lightning
  weights separately for Qwen-Image, Qwen-Image-Edit, Edit-2509, Edit-2511
  and Qwen-Image-2512, so accelerators are family- specific in practice. The
  one documented case worse than mild degradation is precision-level, not
  family-level: bf16-trained LoRAs on the naive
  qwen_image_fp8_e4m3fn.safetensors base produce grid artifacts, stated
  outright in the ModelTC/Qwen-Image-Lightning README. Whether an Edit LoRA
  on the T2I base merely no-ops (no ref_latents conditioning is supplied) or
  a T2I LoRA on an Edit checkpoint transfers as a style push is inference
  from the architecture, not a sourced statement - see unverified.

───────────────────────────────────────────────────────────────────────────────
  AUTHOR'S DESCRIPTION
───────────────────────────────────────────────────────────────────────────────
  Qwen Lightning 8 steps https://huggingface.co/lightx2v/Qwen-Image-Lightning
  Usage:
  Strength: 1.0
  CFG: 1
  Steps: 4 or 8
  Sigma Shift: 0.3-3 YOU are responsible for outputs as always! If you make
  ToS violating content and I get aware I WILL report this.

───────────────────────────────────────────────────────────────────────────────
  EXAMPLE MEDIA
───────────────────────────────────────────────────────────────────────────────
  1 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.webp  (image, 1072x1584)

───────────────────────────────────────────────────────────────────────────────
  HOW TO USE (COMFYUI)
───────────────────────────────────────────────────────────────────────────────
  1. Update ComfyUI first - Qwen-Image support is native, but each new family
  member (Edit-2509, Edit-2511, 2512) needed a fresh release, so an old build
  will not detect the checkpoint.
  2. Put the base checkpoint in `ComfyUI/models/diffusion_models/` - e.g.
  `qwen_image_2512_fp8_e4m3fn.safetensors` (20.43 GB, the file the official
  2512 template names) or `qwen_image_2512_bf16.safetensors` (40.86 GB), from
  huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/split_files/diffusion_models.
  Edit checkpoints come from Comfy-Org/Qwen-Image-Edit_ComfyUI. Load with
  `Load Diffusion Model` (UNETLoader), not a checkpoint loader - these are
  unet-only files.
  3. Put `qwen_2.5_vl_7b_fp8_scaled.safetensors` (9.38 GB) in
  `ComfyUI/models/text_encoders/` and load with `Load CLIP` (CLIPLoader),
  type `qwen_image`. Every official template uses exactly this pair.
  4. Put `qwen_image_vae.safetensors` in `ComfyUI/models/vae/` and load with
  `Load VAE`.
  5. Put LoRA `.safetensors` in `ComfyUI/models/loras/`. Subfolders show up
  as `subfolder/name.safetensors` in the dropdown - useful for separating t2i
  / edit / accelerator LoRAs.
  6. Load with `LoraLoaderModelOnly`, patching only the MODEL line between
  the UNETLoader and ModelSamplingAuraFlow. Every official Comfy-Org Qwen
  template uses LoraLoaderModelOnly; the two-output `LoraLoader` also works
  but its CLIP branch is a no-op for DiT-only LoRAs.
  7. Insert `ModelSamplingAuraFlow` after the LoRA chain. Use 3.1 for T2I and
  Edit-2511, 3.0 for the 2-step Turbo and Edit-2509 templates. Without this
  node ComfyUI uses the model's built-in shift of 1.15 and results differ
  from every published example.
  8. Set KSampler to euler / simple / denoise 1.0, then steps+cfg per the
  accelerator (50/4.0 plain, 8/1.0 or 4/1.0 with Lightning, 2/1.0 with the
  2-step Turbo). Latent from `EmptySD3LatentImage` at an official resolution.
  9. Low-VRAM alternative: the `ComfyUI-GGUF` custom node with `Unet Loader
  (GGUF)` and a Qwen-Image/2512 GGUF (unsloth/Qwen-Image-2512-GGUF). LoRA
  loading still goes through LoraLoaderModelOnly, placed after the GGUF
  loader.
  10. For Edit workflows, swap CLIPTextEncode for `TextEncodeQwenImageEdit`
  (single image) or `TextEncodeQwenImageEditPlus` (2509/2511) and add a
  `CFGNorm` node as the Edit-2511 template does; the LoRA chain sits in the
  same place.

───────────────────────────────────────────────────────────────────────────────
  Scraped by lorakit on 2026-09-08 13:30 UTC.
  Stats and description are the author's; pros/cons are derived from the
  evidence tagged beside each line.
───────────────────────────────────────────────────────────────────────────────

	═══════════════════════════════════════════════════════════════════════════════
	QWEN LIGHTNING LORA
	═══════════════════════════════════════════════════════════════════════════════

	───────────────────────────────────────────────────────────────────────────────
	IDENTITY
	───────────────────────────────────────────────────────────────────────────────
	Base model Qwen-Image
	Generation mode not declared by the author
	Checkpoint not determined — verify before use
	Category Speed / step-reduction
	Author darksidewalker
	Source https://civarchive.com/models/1854805?modelVersionId=2235536
	Provenance CivitAI · model 1854805 · version 2235536

	───────────────────────────────────────────────────────────────────────────────
	WEIGHTS
	───────────────────────────────────────────────────────────────────────────────
	File Qwen-Image-Lightning-8steps-V2.0-bf16.safetensors
	Version Qwen-2.0-bf16-8-Step
	Size 810.2 MB
	Format SafeTensor / unknown precision
	SHA256 5bdbf69912280a9944be9b3aacd8db0cfbb429fcbd66c994d7b38b5a37e357ee
	Published 2025-09-20

	───────────────────────────────────────────────────────────────────────────────
	TRIGGER WORDS
	───────────────────────────────────────────────────────────────────────────────
	No trigger word. The LoRA applies as soon as it is loaded —
	strength is the only way to dial the effect up or down.

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

	LoRA strength 1.0
	Sampler steps 8
	CFG / guidance 1

	───────────────────────────────────────────────────────────────────────────────
	ADOPTION & POPULARITY
	───────────────────────────────────────────────────────────────────────────────
	Downloads 8,785
	Rating no votes yet
	Comments 32
	Published 353 days ago
	Download rate 24.9/day since release

	Adoption rank #36 of 200 in this collection (High)
	Momentum rank #11 of 200 by download rate (Hot)

	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 Qwen-Image ones, not anything specific to this LoRA.

	General Qwen-Image rules that apply here (see REFERENCE.txt):

	• Stack by wiring LoraLoaderModelOnly nodes in series on the MODEL line.
	This is the officially shipped pattern:
	template_qwen_Image_2512_360_lora chains Qwen-
	Image-2512-Lightning-4steps-V1.0-fp32 at 1.0 into
	qwen-360-diffusion-2512-int8-bf16-v2 at 1.0.
	• One accelerator LoRA maximum. Every official template loads exactly one
	Lightning/Turbo LoRA, and ComfyUI's Qwen-Image docs record that the
	fully-distilled checkpoint and the lightx2v 8-step LoRA are not usable
	together.
	• Match the accelerator to the checkpoint family: Qwen-
	Image-2512-Lightning on 2512, Qwen-Image-Lightning on the August base,
	the Edit-2509 subfolder LoRAs on Edit-2509, Qwen-Image-
	Edit-2511-Lightning on Edit-2511. lightx2v distilled and shipped these
	separately per family.
	• When any accelerator LoRA is in the chain, move the sampler to that
	LoRA's step count and cfg 1.0. Leaving cfg at 4.0 with a distilled LoRA
	is the most common bad-output cause.
	• Order used by the official templates: accelerator LoRA adjacent to the
	base loader, concept/style LoRA after it, then ModelSamplingAuraFlow,
	then the sampler (the 360-panorama template's exact order).
	• Keep the summed strength of concept/style LoRAs roughly in the 0.9-1.2
	band (CivitAI article 18798). The accelerator LoRA sits outside that
	budget at its own 1.0.
	• Control LoRAs (qwen_image_union_diffsynth_lora.safetensors) chain like
	ordinary LoRAs and combine with an accelerator: the official 'Qwen-
	Image Union Control' template stacks the control LoRA with Qwen-Image-
	Lightning-4steps-V1.0, both at 1.0, sampling at 4 steps / cfg 1.0 /
	shift 3.1.
	• Be conservative stacking older Edit LoRAs on Edit-2511: the Qwen README
	says community LoRA effects were merged into the 2511 base, so those
	LoRAs can double-apply.
	• The dominant family is Qwen-Image-Lightning by lightx2v / ModelTC
	(github.com/ModelTC/Qwen-Image-Lightning), CFG-distilled LoRAs released
	per checkpoint family. 2512 Lightning files are 0.85 GB in bf16 and
	1.70 GB in fp32 - high-rank LoRAs, not small ones. Repo layout
	(verified against the HF file listings): lightx2v/Qwen-Image-Lightning
	holds the T2I LoRAs (4steps-V1.0, 4steps-V2.0, 8steps-V1.0,
	8steps-V1.1, 8steps-V2.0, each also in -bf16), a Qwen-Image-fp8-e4m3fn-
	Lightning-4steps-V1.0 distilled against the naive fp8 base, the
	original Qwen-Image-Edit Lightning 4/8-step files, an Edit-2509 s
	• The author never states which weight family this targets. Mismatch is
	silent degradation, essentially never a hard error. Every Qwen-Image
	weight family resolves to the same ComfyUI model class
	(comfy.model_base.QwenImage, unet_config image_model "qwen_image",
	latent_format Wan21, built-in sampling shift 1.15 -
	comfy/supported_models.py

	───────────────────────────────────────────────────────────────────────────────
	PROS
	───────────────────────────────────────────────────────────────────────────────
	+ Widely adopted — 8,785 downloads. [source: CivitAI stats]
	+ Author published concrete recommended settings. [source: description]

	───────────────────────────────────────────────────────────────────────────────
	CONS & CAVEATS
	───────────────────────────────────────────────────────────────────────────────
	- No trigger word — the LoRA is always on once loaded, so strength is the
	only control. [source: model metadata]
	- Author never states which generation mode it was trained for; test
	against your own workflow before relying on it. [source: description]
	- Large at 810 MB — slower to load and heavier to stack. [source: file
	size]

	───────────────────────────────────────────────────────────────────────────────
	COMPATIBILITY WARNING
	───────────────────────────────────────────────────────────────────────────────
	Mismatch is silent degradation, essentially never a hard error. Every Qwen-
	Image weight family resolves to the same ComfyUI model class
	(comfy.model_base.QwenImage, unet_config image_model "qwen_image",
	latent_format Wan21, built-in sampling shift 1.15 -
	comfy/supported_models.py), and the bf16/fp8 file sizes are identical
	across Qwen-Image, Qwen-Image-2512, Qwen-Image-Edit, Edit-2509 and
	Edit-2511. So a LoRA trained on any of them will key-match and load against
	any other. Where keys genuinely do not match, ComfyUI only logs `lora key
	not loaded: <key>` (comfy/lora.py:93) and continues; a shape mismatch logs
	`WARNING SHAPE MISMATCH <key> WEIGHT NOT MERGED` (comfy/lora.py:498) and
	skips that tensor. Both are console warnings; the render still completes.
	Verified consequence: lightx2v re-distilled and re-released Lightning
	weights separately for Qwen-Image, Qwen-Image-Edit, Edit-2509, Edit-2511
	and Qwen-Image-2512, so accelerators are family- specific in practice. The
	one documented case worse than mild degradation is precision-level, not
	family-level: bf16-trained LoRAs on the naive
	qwen_image_fp8_e4m3fn.safetensors base produce grid artifacts, stated
	outright in the ModelTC/Qwen-Image-Lightning README. Whether an Edit LoRA
	on the T2I base merely no-ops (no ref_latents conditioning is supplied) or
	a T2I LoRA on an Edit checkpoint transfers as a style push is inference
	from the architecture, not a sourced statement - see unverified.

	───────────────────────────────────────────────────────────────────────────────
	AUTHOR'S DESCRIPTION
	───────────────────────────────────────────────────────────────────────────────
	Qwen Lightning 8 steps https://huggingface.co/lightx2v/Qwen-Image-Lightning
	Usage:
	Strength: 1.0
	CFG: 1
	Steps: 4 or 8
	Sigma Shift: 0.3-3 YOU are responsible for outputs as always! If you make
	ToS violating content and I get aware I WILL report this.

	───────────────────────────────────────────────────────────────────────────────
	EXAMPLE MEDIA
	───────────────────────────────────────────────────────────────────────────────
	1 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.webp (image, 1072x1584)

	───────────────────────────────────────────────────────────────────────────────
	HOW TO USE (COMFYUI)
	───────────────────────────────────────────────────────────────────────────────
	1. Update ComfyUI first - Qwen-Image support is native, but each new family
	member (Edit-2509, Edit-2511, 2512) needed a fresh release, so an old build
	will not detect the checkpoint.
	2. Put the base checkpoint in `ComfyUI/models/diffusion_models/` - e.g.
	`qwen_image_2512_fp8_e4m3fn.safetensors` (20.43 GB, the file the official
	2512 template names) or `qwen_image_2512_bf16.safetensors` (40.86 GB), from
	huggingface.co/Comfy-Org/Qwen-Image_ComfyUI/split_files/diffusion_models.
	Edit checkpoints come from Comfy-Org/Qwen-Image-Edit_ComfyUI. Load with
	`Load Diffusion Model` (UNETLoader), not a checkpoint loader - these are
	unet-only files.
	3. Put `qwen_2.5_vl_7b_fp8_scaled.safetensors` (9.38 GB) in
	`ComfyUI/models/text_encoders/` and load with `Load CLIP` (CLIPLoader),
	type `qwen_image`. Every official template uses exactly this pair.
	4. Put `qwen_image_vae.safetensors` in `ComfyUI/models/vae/` and load with
	`Load VAE`.
	5. Put LoRA `.safetensors` in `ComfyUI/models/loras/`. Subfolders show up
	as `subfolder/name.safetensors` in the dropdown - useful for separating t2i
	/ edit / accelerator LoRAs.
	6. Load with `LoraLoaderModelOnly`, patching only the MODEL line between
	the UNETLoader and ModelSamplingAuraFlow. Every official Comfy-Org Qwen
	template uses LoraLoaderModelOnly; the two-output `LoraLoader` also works
	but its CLIP branch is a no-op for DiT-only LoRAs.
	7. Insert `ModelSamplingAuraFlow` after the LoRA chain. Use 3.1 for T2I and
	Edit-2511, 3.0 for the 2-step Turbo and Edit-2509 templates. Without this
	node ComfyUI uses the model's built-in shift of 1.15 and results differ
	from every published example.
	8. Set KSampler to euler / simple / denoise 1.0, then steps+cfg per the
	accelerator (50/4.0 plain, 8/1.0 or 4/1.0 with Lightning, 2/1.0 with the
	2-step Turbo). Latent from `EmptySD3LatentImage` at an official resolution.
	9. Low-VRAM alternative: the `ComfyUI-GGUF` custom node with `Unet Loader
	(GGUF)` and a Qwen-Image/2512 GGUF (unsloth/Qwen-Image-2512-GGUF). LoRA
	loading still goes through LoraLoaderModelOnly, placed after the GGUF
	loader.
	10. For Edit workflows, swap CLIPTextEncode for `TextEncodeQwenImageEdit`
	(single image) or `TextEncodeQwenImageEditPlus` (2509/2511) and add a
	`CFGNorm` node as the Edit-2511 template does; the LoRA chain sits in the
	same place.

	───────────────────────────────────────────────────────────────────────────────
	Scraped by lorakit on 2026-09-08 13:30 UTC.
	Stats and description are the author's; pros/cons are derived from the
	evidence tagged beside each line.
	───────────────────────────────────────────────────────────────────────────────