No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from Alissonerdx/EditAnything
All models by Alissonerdx →Heads up. These LoRAs are research experiments. They are far from production-ready and will fail on many inputs. They are released for the community to play with and break, not as a finished tool.
This repository hosts four unrelated training tracks:
Tracks 1-3 are LTX-2.3 and are kept for reference. Track 0 is LTX-2.5 and is the one being worked on.
Inference is meant to run through the BFSnodes ComfyUI custom nodes — the Ref V2V build in particular needs them to load the sidecar modules and install the custom branches into the transformer.
File: edit_anything_v2_ltx2.5.safetensors (rank 128)
Workflow: workflows/EditAnythingLTX2.5.json
Base model: LTX-2.5 22B dev
In this experimental version it is possible to perform several operations together in a single prompt — Replace, Remove, Add, Restyle — and everything becomes easier with the help of the prompt enhancer, so you can write in natural language and it converts it to the appropriate prompt.
Unlike track 3, this LoRA takes no reference image. It is a plain IC-LoRA: your source video goes in as the guide, the instruction goes in as text, and the edited video comes out. No RoPE tricks, no sidecar modules, no loss masks — the simplest thing that works.
Each clip is a three-panel comparison: source guide | first pass | second pass (upscaled).
Example 1
Example 2
Example 3
Example 4
Example 5
Load workflows/EditAnythingLTX2.5.json. If you are wiring it by hand with the BFSnodes
LTX Multiple Controls node, the settings that match training are:
Leave identity_image, mask_video and identity_mask_image disconnected — this LoRA
was trained without any of them.
Trained resolution is 704x384, 73 frames. Other sizes and lengths are extrapolation and
degrade first in temporal consistency. Suggested start: LoRA strength 1.0, CFG 3-5,
30 steps, no LightX2V.
Every prompt starts with the trigger:
Then one sentence per edit. These four verbs are the only ones the model understands, listed from most to least reliable:
Rules that matter — breaking them is the usual reason a prompt does nothing:
Add. Write Add a ... / Add an .... For a group or a crowd use
Replace on an existing region instead of Add several ....Restyle targets a region, not the whole clip. Name a wall, a screen, a background or
a face. For a whole-video look, write two or three Restyle instructions over the regions
that carry it.Make it <style> and Turn it into <style> do not work. Use Restyle.Examples in the exact shape the model expects:
Write one instruction per edit you actually want. Do not pad the prompt with edits you did not ask for — an unrequested sky or background change will show up in the output.
Trained from scratch on LTX-2.5 22B dev — not a continuation of the LTX-2.3 LoRAs in this repository. 2750 aligned source/edited video pairs, rank 128 / alpha 128, at 704x384, 73 frames.
Files:
edit_anything_30k_v0.1_motion_transfer_r128.safetensorsedit_anything_30k_v0.1_motion_transfer_r256.safetensorsv0.1 is not a direct continuation of v1.0. It was trained from scratch in two stages:
first_frame_conditioning > 0. This
restored the temporal prior and unlocked the motion-transfer behaviour
described below.In theory v0.1 can do the same edits as v1.0, but temporal consistency may be weaker than v1.0 because so much of stage 1 happened on still images. Test against v1.0 case-by-case before assuming v0.1 wins on your task.
Because stage 2 included first-frame conditioning, you can drive the LoRA into a motion-transfer mode:
The model uses the new first frame as the appearance anchor and copies the motion from the rest of the guide.
Limitations (these are real, not theoretical — expect them to bite):
Prompt is just as critical as in v1.0. Describe both the object being replaced and the new one in detail. Example: "Replace the bronze statue on the left with a tall man wearing a navy raincoat and brown boots." Vague prompts produce bad edits.
The same training produced both files. v0.1 is actually the merge of the two-stage training (one LoRA per stage), re-extracted at two different ranks via Frobenius-optimal truncated SVD:
r256 is closer to the merged source. r128 is normally indistinguishable in practice. Pick whichever fits your workflow.
This is a standard LoRA, not a sidecar. Load it through the regular ComfyUI LoraLoader before the LoopingSampler. On the sampler itself:
editanything_module → leave disconnected.ref_image → the edited first frame (for motion transfer) or the
source frame you want preserved (for plain editing).guide_frames → the guide video.enable_role_embedding, enable_adaln, enable_visual_crossattn →
all off. None of those branches were trained for v0.1; turning them
on with no module connected does nothing anyway, but keeping them off
silences the WARN logs.File:
edit_anything_v1.1_r256.safetensorsA prompt-only multitask editing LoRA. No reference image, no first-frame conditioning — the model is driven entirely by the text prompt and the guide video. Trained on a balanced mix of Add, Remove, Replace, Style edits.
The task vocabulary overlaps heavily with v0.1 — both can do Add, Remove, Replace, Change, Convert. What changes here:
Standalone — load it as a regular LoRA on vanilla LTX-2.3 through any ComfyUI LoRA loader. The file already carries everything it needs; no stacking with v0.1, no companion module.
Same imperative shape as v0.1, but the training set split into four very distinct caption styles. Match the one that fits the edit you want — the distribution is narrow and the model expects the right shape.
The training set is roughly balanced across Add, Remove, Replace and Style buckets, with Style being the smallest of the four. Captions below are real examples drawn from those buckets.
Add a smiling woman with brown hair, wearing a pink sleeveless top, sitting to the right of the man at the news desk.Add a person wearing a blue denim shirt over a white t-shirt to the right side of the frame, behind the person cooking.Add a decorated Christmas tree with red and white ornaments and lights to the right of the man.Add a blonde boy wearing a black t-shirt with a blue collar and blue patterned pants, sitting behind the other children in the upper center of the frame.Add two horizontal wooden strips to the front of the white range hood.Pattern: Add <detailed subject description>, <position in frame>, <surrounding context>.
Remove the man drinking from a glass.Remove the disco ball.Remove the large tree on the right.Remove the squirrel in the foreground.Remove the man on the left.Pattern: Remove the <object> (+ optional position). Resist the urge to
over-describe — long Remove prompts drift outside the training shape and
often fail.
Replace the white panel door on the right side of the frame with a dark brown grandfather clock.Replace the light-colored cat lying on the mat on the floor with a young woman sitting on the mat.Replace the dark grey knitted sweater on the man's torso with a black and white patterned Christmas sweater.Replace the blue robot with a glowing blue face on the left with a smiling man wearing sunglasses and a blue shirt.Replace the sitting person wearing a black cape on the left with a black fabric draped over an object.Pattern: Replace <description of the original subject and its location> with <description of the new subject>.
Convert the video into a Pencil Sketch style.Convert the video into a Watercolor Painting style.Convert the video into a Van Gogh style.Convert the video into a Play-Doh style.Convert the video into a Claymation style.Convert the video into a 3D Chibi style.Convert the video into a Ghibli style.Convert the video into a Pop Art style.Convert the video into an American Cartoon style.Convert the video into a Flat Vector Cartoon style.The training set covers 300+ distinct style names. Many work; many do
not. The list above is heavily represented in training. Use the exact
phrase Convert the video into a <STYLE> style — deviations from this
template degrade quality noticeably.
These are honest limits of the training distribution — don't expect them to work just because the model is multitask:
A single standard LoRA, no sidecar, no stacking. Load through one ComfyUI LoraLoader before the LoopingSampler. On the sampler:
editanything_module → leave disconnected.ref_image → leave disconnected. This LoRA has no reference-image
path; passing one will just pre-encode tokens that you do not want.guide_frames → the guide video.enable_role_embedding, enable_adaln, enable_visual_crossattn →
all off (no module = nothing to inject anyway).Files (two builds of the same LoRA family — each ships as a (.standard, .module) pair):
edit_anything_reference_v0.1_r128_ref_adaln_proj-role_embedding.standard.safetensorsedit_anything_reference_v0.1_r128_ref_adaln_proj-role_embedding.module.safetensorsedit_anything_reference_v0.1_r128_ref_adaln_proj-role_embedding-ref_attn-ref_visual_proj.standard.safetensorsedit_anything_reference_v0.1_r128_ref_adaln_proj-role_embedding-ref_attn-ref_visual_proj.module.safetensorsThe goal is add / replace using a reference image — same vibe as Edit Anything v1.0, but with an explicit image as the appearance source instead of relying only on the prompt.
Trained on ~1600 Add / Replace video pairs. Reference-paired video datasets are basically nonexistent, so the dataset had to be built from scratch — that is why the sample count is small. It often fails. This is fully experimental; thousands of training runs went into landing on this LoRA layout, and it is still unclear how much it actually helps.
Trained as a conventional IC-LoRA, plus extra projection branches that try to make the reference signal survive across layers:
ref_visual_proj — projects the reference VAE latent into 32 visual
memory tokens.ref_attn — a dedicated cross-attention branch inside each
transformer block, reading those tokens.ref_adaln_proj — a global AdaLN bias derived from the reference
(palette / overall look).role_embedding — an experimental token bias inspired by some of
Kijai's tests; whether it actually helps is still unclear.These extra weights are saved alongside the LoRA in a .module.safetensors
sidecar because they are not standard LoRA adapters — the regular
ComfyUI LoRA loader can't consume them, so they need a dedicated node.
Both files of a pair must be loaded together — the LoRA was trained
against the sidecar adapters and they only make sense as a unit. Do not mix
.standard from one build with .module from another.
The module file is consumed by the 🅛🅣🅧 LTXV Edit Anything Looping Sampler node, which was written specifically to:
ref_attn cross-attention branch on every transformer block.*.standard.safetensors through a normal ComfyUI LoraLoader
before the sampler.*.module.safetensors through LTXVEditAnythingModuleLoader
and connect its editanything_module output to the sampler.editanything_module → the module loader output (required).ref_image → the reference image (required — this is what
Add / Replace will insert).guide_frames → the source video to edit.enable_adaln → on (defaults match training).enable_visual_crossattn → on for the 4-extras build; off (or
will be a no-op) for the 2-extras build.enable_role_embedding → off for the 4-extras build (training
config disabled it). On if you're loading the 2-extras build alone.Missing ref_image here silently disables AdaLN and the visual
cross-attention — the sampler will warn in the log.
ref_adaln_proj-role_embedding — the original training. Only ships
the two side-channel modules.ref_adaln_proj-role_embedding-ref_attn-ref_visual_proj — the
continuation. Adds the visual cross-attention branch and its projector on
top.It is genuinely not clear yet whether the extra branches help over the plain LoRA. Both builds are honest experiments. Try both, decide for your own use case, and please share findings.
For anyone who wants to understand what each layer in the Ref V2V checkpoint does:
lora_layers_reference.md — full tensor
inventory of both builds.lora_layers_impact.md — what each branch
contributes at inference and which inference knob (adaln_scale,
ref_context_scale, ref_token_scale, ref_start_block,
ref_end_block, etc.) maps back to which training default.The two LoRAs were trained on very different caption styles. Match the style of whichever LoRA you're using — straying outside the training distribution is the fastest way to get garbage out.
The stage-1 dataset uses short imperative captions describing one or two edits. Use the same shape at inference. Examples drawn from the training distribution:
Tips:
Workflow:
Examples:
Limits: fast or chaotic motion will fail; the inserted subject should occupy roughly the same region/scale as what it replaces.
These captions are real samples from the ~1600-pair training set. They describe the target scene after the edit in detail. The reference image carries the appearance of the inserted subject; the caption carries position, pose, action, and surrounding context.
Add task (the reference image holds the new subject):
Replace task (the reference image holds the new subject; the caption also describes what is being replaced):
Tips for Ref V2V:
CFG matters a lot here. The default workflow runs with the LTX-2.3 distilled / acceleration LoRAs for fast 4–8 step sampling, which locks CFG = 1.0. That's fine for casual runs, but at CFG 1 the model follows the prompt loosely — you get the reference image to "show up" but the edit instruction itself is only weakly enforced.
For harder prompts, raise CFG above 1.0. This means dropping (or weakening) the distilled / acceleration LoRAs and going back to a normal sampler with more steps — significantly slower, but the model follows the prompt much more closely. Trade-off:
Other knobs:
adaln_scale, ref_context_scale, ref_token_scale for Ref V2V;
prompt rewriting for v0.1 / no-ref).Treat CFG as a real knob, not a constant — and be ready to give up some speed when you actually need the edit to land.
All recommended inference paths run through the BFSnodes custom node set. For now BFSnodes is the only place these nodes live; once they stabilise they may move elsewhere.
Specific nodes used by these LoRAs:
LTXVEditAnythingApply — load the LoRA + extras and patch the model.🅛🅣🅧 LTXV Edit Anything Looping Sampler — sampler that injects role /
AdaLN / visual cross-attention and handles long videos in chunks.LTXVEditAnythingModuleLoader — load the *.module.safetensors sidecar.Released as experimental research artefacts. Expect failures, do not deploy, and please report what works and what doesn't.
If you use these models — in a project, a demo, a paper, a video, a tweet, a workflow, anything — please credit my work. These checkpoints are the result of weeks of research, dataset building, and training runs, and that effort is what makes any of it usable. Crediting the source is the bare minimum that keeps open research like this sustainable.
Author: Alisson Pereira dos Anjos (@Alissonerdx)
Suggested attribution:
Edit Anything LoRAs by Alisson Pereira dos Anjos (huggingface.co/Alissonerdx/EditAnything).
Links back to this repository are appreciated wherever you publish results.
edit_anything: Replace the green indoor background with a sandy beach under a bright sky, where the mandances in dark blue swim trunks and a white beach towel draped over his shoulder, holding ayellow inflatable ring around his waist.edit_anything: Replace the purple Dodge Challenger in the background with a green Lamborghini Huracan,featuring black five-spoke wheels and a low front splitter. The woman remains fully visiblethroughout the video, wearing her brown suit as she dances in the foreground.edit_anything: Add a cinematic apocalyptic scene with falling bombs and explosive detonations, creatingdramatic smoke and debris as the blue sports car races through the curves.edit_anything: Replace the woman's dark black hair with vibrant red hair. Add a metallic leathermetalworker outfit, including a sleeveless top and pants, worn by her in the center of theframe.edit_anything: Add a pair of dark-framed sunglasses resting on the man's face in all scenes.edit_anything:Replace <the existing thing> with <the new thing, described>.Add a <object with attributes> <where>.Remove <the thing, identified precisely>.Restyle <the region, identified> into <style> style.edit_anything: Add a medium-sized brown dog sitting on the grass to the right of themotorcycles. Remove the black jacket worn by the smiling man in the left foreground.Replace the man's graying hair with bright red hair.
edit_anything: Replace the gray and black hoodie worn by the man with a bright red zip-upjacket with white stripes on the sleeves.
edit_anything: Remove the smartphone held in the man's hand.
edit_anything: Restyle the large blue digital screen behind the man into flat vector style.